coding-agents
tool-selection
bialy / evidence /tool-validation.json
paintedwolf-ai's picture
Release open1-b5-e4-bialy
39012d0 verified
Raw History Blame Contribute Delete
37.5 kB
{
"scope": "Existing validation distribution; threshold selection, not fresh final acceptance.",
"comparison": "Two complete configurations on the same validation rows: B2 joint encoding with six-word tool options; B5 independent encoding with up to 60-word options. Corpus hashes intentionally differ.",
"transformation": "Per-tool breakdowns omitted; all aggregate threshold rows retained without recalculation.",
"prediction_metadata_sha256": "de8a6974d1ca4a615f319089b2a6b023e5e57ede9bc03e52de5aa9524bde11c9",
"reports": {
"B2": {
"original_report_sha256": "4b705b7e02a4307e3d23898691c6e82fc72fcfbe9d4e94c0c0341838af21d206",
"input_sha256": {
"predictions": "b20f3ddf176f4a5905ac1a4a3073e41a1c4833a930292c942abbba974c10c9b1",
"rows": "67c4c86e3385f0241048f2633d97a4aad78a53a3b7a540592937a20eba669fd3",
"corpus": "51e3a65258fc34581bc8cfaae0f7c97f444f0a50f3dda906c77b6554fd5c66d3"
},
"prediction_metadata_sha256": "e8d91777999dded4eafe02cf46d7e99a3a89b0bd376c7f6922519e33f7e360dd",
"encoding": "joint",
"tool_option_words": 6,
"head_sha256": "bc432ea7497e9300e39230ee9850de8f42e3f9a3cbbf372259263c49c77011e4",
"truth": {
"consensus": [
{
"threshold": 0.5,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 935,
"empty": 128,
"needed_turns": 216,
"any_needed_loaded": 173,
"all_needed_loaded": 149,
"tn": 29289,
"fp": 509,
"tp": 203,
"unknown_loaded": 223,
"fn": 82
},
"precision": 0.2851123595505618,
"recall": 0.712280701754386,
"f0.5": 0.3239706351739547,
"loads_per_turn": 2.101123595505618,
"empty_turn_rate": 0.2876404494382023
},
{
"threshold": 0.6,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 734,
"empty": 158,
"needed_turns": 216,
"any_needed_loaded": 159,
"all_needed_loaded": 137,
"tn": 29438,
"fp": 360,
"tp": 186,
"unknown_loaded": 188,
"fn": 99
},
"precision": 0.34065934065934067,
"recall": 0.6526315789473685,
"f0.5": 0.37667071688942894,
"loads_per_turn": 1.649438202247191,
"empty_turn_rate": 0.3550561797752809
},
{
"threshold": 0.7,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 533,
"empty": 189,
"needed_turns": 216,
"any_needed_loaded": 147,
"all_needed_loaded": 122,
"tn": 29576,
"fp": 222,
"tp": 166,
"unknown_loaded": 145,
"fn": 119
},
"precision": 0.42783505154639173,
"recall": 0.5824561403508772,
"f0.5": 0.4518236254763201,
"loads_per_turn": 1.1977528089887641,
"empty_turn_rate": 0.4247191011235955
},
{
"threshold": 0.75,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 419,
"empty": 220,
"needed_turns": 216,
"any_needed_loaded": 131,
"all_needed_loaded": 105,
"tn": 29640,
"fp": 158,
"tp": 147,
"unknown_loaded": 114,
"fn": 138
},
"precision": 0.4819672131147541,
"recall": 0.5157894736842106,
"f0.5": 0.4883720930232558,
"loads_per_turn": 0.9415730337078652,
"empty_turn_rate": 0.4943820224719101
},
{
"threshold": 0.8,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 301,
"empty": 262,
"needed_turns": 216,
"any_needed_loaded": 108,
"all_needed_loaded": 83,
"tn": 29703,
"fp": 95,
"tp": 117,
"unknown_loaded": 89,
"fn": 168
},
"precision": 0.5518867924528302,
"recall": 0.4105263157894737,
"f0.5": 0.5163283318623124,
"loads_per_turn": 0.6764044943820224,
"empty_turn_rate": 0.5887640449438202
},
{
"threshold": 0.85,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 211,
"empty": 299,
"needed_turns": 216,
"any_needed_loaded": 93,
"all_needed_loaded": 72,
"tn": 29745,
"fp": 53,
"tp": 100,
"unknown_loaded": 58,
"fn": 185
},
"precision": 0.6535947712418301,
"recall": 0.3508771929824561,
"f0.5": 0.5574136008918618,
"loads_per_turn": 0.47415730337078654,
"empty_turn_rate": 0.6719101123595506
},
{
"threshold": 0.89,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 151,
"empty": 326,
"needed_turns": 216,
"any_needed_loaded": 80,
"all_needed_loaded": 60,
"tn": 29771,
"fp": 27,
"fn": 201,
"unknown_loaded": 40,
"tp": 84
},
"precision": 0.7567567567567568,
"recall": 0.29473684210526313,
"f0.5": 0.5761316872427984,
"loads_per_turn": 0.3393258426966292,
"empty_turn_rate": 0.7325842696629213
},
{
"threshold": 0.9,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 138,
"empty": 336,
"needed_turns": 216,
"any_needed_loaded": 74,
"all_needed_loaded": 56,
"tn": 29773,
"fp": 25,
"fn": 207,
"unknown_loaded": 35,
"tp": 78
},
"precision": 0.7572815533980582,
"recall": 0.2736842105263158,
"f0.5": 0.5595408895265424,
"loads_per_turn": 0.3101123595505618,
"empty_turn_rate": 0.755056179775281
},
{
"threshold": 0.95,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 84,
"empty": 373,
"needed_turns": 216,
"any_needed_loaded": 51,
"all_needed_loaded": 43,
"tn": 29789,
"fn": 230,
"unknown_loaded": 20,
"tp": 55,
"fp": 9
},
"precision": 0.859375,
"recall": 0.19298245614035087,
"f0.5": 0.5083179297597042,
"loads_per_turn": 0.18876404494382024,
"empty_turn_rate": 0.8382022471910112
},
{
"threshold": 0.97,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 62,
"empty": 391,
"needed_turns": 216,
"any_needed_loaded": 41,
"all_needed_loaded": 34,
"tn": 29793,
"fn": 241,
"unknown_loaded": 13,
"tp": 44,
"fp": 5
},
"precision": 0.8979591836734694,
"recall": 0.1543859649122807,
"f0.5": 0.4573804573804574,
"loads_per_turn": 0.1393258426966292,
"empty_turn_rate": 0.8786516853932584
},
{
"threshold": 0.99,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 29,
"empty": 417,
"needed_turns": 216,
"any_needed_loaded": 21,
"all_needed_loaded": 15,
"tn": 29795,
"fn": 264,
"unknown_loaded": 5,
"tp": 21,
"fp": 3
},
"precision": 0.875,
"recall": 0.07368421052631578,
"f0.5": 0.2755905511811024,
"loads_per_turn": 0.0651685393258427,
"empty_turn_rate": 0.9370786516853933
}
],
"called": [
{
"threshold": 0.5,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 935,
"empty": 128,
"needed_turns": 228,
"any_needed_loaded": 182,
"all_needed_loaded": 91,
"tn": 29888,
"fp": 659,
"tp": 276,
"fn": 248
},
"precision": 0.29518716577540105,
"recall": 0.5267175572519084,
"f0.5": 0.3236397748592871,
"loads_per_turn": 2.101123595505618,
"empty_turn_rate": 0.2876404494382023
},
{
"threshold": 0.6,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 734,
"empty": 158,
"needed_turns": 228,
"any_needed_loaded": 166,
"all_needed_loaded": 76,
"tn": 30053,
"fp": 494,
"tp": 240,
"fn": 284
},
"precision": 0.32697547683923706,
"recall": 0.4580152671755725,
"f0.5": 0.3468208092485549,
"loads_per_turn": 1.649438202247191,
"empty_turn_rate": 0.3550561797752809
},
{
"threshold": 0.7,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 533,
"empty": 189,
"needed_turns": 228,
"any_needed_loaded": 149,
"all_needed_loaded": 59,
"tn": 30208,
"tp": 194,
"fp": 339,
"fn": 330
},
"precision": 0.36397748592870544,
"recall": 0.3702290076335878,
"f0.5": 0.36521084337349397,
"loads_per_turn": 1.1977528089887641,
"empty_turn_rate": 0.4247191011235955
},
{
"threshold": 0.75,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 419,
"empty": 220,
"needed_turns": 228,
"any_needed_loaded": 133,
"all_needed_loaded": 46,
"tn": 30286,
"fn": 366,
"fp": 261,
"tp": 158
},
"precision": 0.37708830548926014,
"recall": 0.3015267175572519,
"f0.5": 0.35909090909090907,
"loads_per_turn": 0.9415730337078652,
"empty_turn_rate": 0.4943820224719101
},
{
"threshold": 0.8,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 301,
"empty": 262,
"needed_turns": 228,
"any_needed_loaded": 106,
"all_needed_loaded": 38,
"tn": 30368,
"fn": 402,
"fp": 179,
"tp": 122
},
"precision": 0.4053156146179402,
"recall": 0.23282442748091603,
"f0.5": 0.35300925925925924,
"loads_per_turn": 0.6764044943820224,
"empty_turn_rate": 0.5887640449438202
},
{
"threshold": 0.85,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 211,
"empty": 299,
"needed_turns": 228,
"any_needed_loaded": 83,
"all_needed_loaded": 32,
"tn": 30430,
"fn": 430,
"fp": 117,
"tp": 94
},
"precision": 0.44549763033175355,
"recall": 0.17938931297709923,
"f0.5": 0.3435672514619883,
"loads_per_turn": 0.47415730337078654,
"empty_turn_rate": 0.6719101123595506
},
{
"threshold": 0.89,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 151,
"empty": 326,
"needed_turns": 228,
"any_needed_loaded": 72,
"all_needed_loaded": 24,
"tn": 30474,
"fn": 446,
"fp": 73,
"tp": 78
},
"precision": 0.5165562913907285,
"recall": 0.14885496183206107,
"f0.5": 0.34574468085106386,
"loads_per_turn": 0.3393258426966292,
"empty_turn_rate": 0.7325842696629213
},
{
"threshold": 0.9,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 138,
"empty": 336,
"needed_turns": 228,
"any_needed_loaded": 65,
"all_needed_loaded": 22,
"tn": 30479,
"fn": 454,
"fp": 68,
"tp": 70
},
"precision": 0.5072463768115942,
"recall": 0.13358778625954199,
"f0.5": 0.3252788104089219,
"loads_per_turn": 0.3101123595505618,
"empty_turn_rate": 0.755056179775281
},
{
"threshold": 0.95,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 84,
"empty": 373,
"needed_turns": 228,
"any_needed_loaded": 42,
"all_needed_loaded": 15,
"tn": 30508,
"fn": 479,
"tp": 45,
"fp": 39
},
"precision": 0.5357142857142857,
"recall": 0.08587786259541985,
"f0.5": 0.2616279069767442,
"loads_per_turn": 0.18876404494382024,
"empty_turn_rate": 0.8382022471910112
},
{
"threshold": 0.97,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 62,
"empty": 391,
"needed_turns": 228,
"any_needed_loaded": 32,
"all_needed_loaded": 9,
"tn": 30520,
"fn": 489,
"tp": 35,
"fp": 27
},
"precision": 0.5645161290322581,
"recall": 0.06679389312977099,
"f0.5": 0.2266839378238342,
"loads_per_turn": 0.1393258426966292,
"empty_turn_rate": 0.8786516853932584
},
{
"threshold": 0.99,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 29,
"empty": 417,
"needed_turns": 228,
"any_needed_loaded": 15,
"all_needed_loaded": 5,
"tn": 30533,
"fn": 509,
"tp": 15,
"fp": 14
},
"precision": 0.5172413793103449,
"recall": 0.02862595419847328,
"f0.5": 0.1171875,
"loads_per_turn": 0.0651685393258427,
"empty_turn_rate": 0.9370786516853933
}
]
}
},
"B5": {
"original_report_sha256": "18a25333e07dfb5b79c6709cf7c99855517ce07e51e3cd80ccc8e15e8a656a51",
"input_sha256": {
"predictions": "e70357d58524a0714882aef5c5de98a6c4cf74a3ad82ae23ee1ed9f97789d1c0",
"rows": "67c4c86e3385f0241048f2633d97a4aad78a53a3b7a540592937a20eba669fd3",
"corpus": "c77abd8b40965c05cc43a7545e8c2db2405bdcfc18a73bad254632d523b67bcd"
},
"prediction_metadata_sha256": "de8a6974d1ca4a615f319089b2a6b023e5e57ede9bc03e52de5aa9524bde11c9",
"encoding": "independent",
"tool_option_words": 60,
"head_sha256": "550f30b94d5c6a8680d2cb2a607ebc9ee33e709c7679f72606d1e9fda17f2e90",
"truth": {
"consensus": [
{
"threshold": 0.5,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 639,
"empty": 176,
"needed_turns": 216,
"any_needed_loaded": 166,
"all_needed_loaded": 141,
"tn": 29523,
"fp": 275,
"tp": 197,
"unknown_loaded": 167,
"fn": 88
},
"precision": 0.4173728813559322,
"recall": 0.6912280701754386,
"f0.5": 0.45329038196042337,
"loads_per_turn": 1.4359550561797754,
"empty_turn_rate": 0.3955056179775281
},
{
"threshold": 0.6,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 539,
"empty": 191,
"needed_turns": 216,
"any_needed_loaded": 164,
"all_needed_loaded": 138,
"tn": 29594,
"fp": 204,
"tp": 192,
"unknown_loaded": 143,
"fn": 93
},
"precision": 0.48484848484848486,
"recall": 0.6736842105263158,
"f0.5": 0.5136436597110754,
"loads_per_turn": 1.2112359550561798,
"empty_turn_rate": 0.42921348314606744
},
{
"threshold": 0.7,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 429,
"empty": 222,
"needed_turns": 216,
"any_needed_loaded": 145,
"all_needed_loaded": 118,
"tn": 29653,
"fp": 145,
"tp": 167,
"unknown_loaded": 117,
"fn": 118
},
"precision": 0.5352564102564102,
"recall": 0.5859649122807018,
"f0.5": 0.5446836268754077,
"loads_per_turn": 0.9640449438202248,
"empty_turn_rate": 0.49887640449438203
},
{
"threshold": 0.75,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 371,
"empty": 238,
"needed_turns": 216,
"any_needed_loaded": 136,
"all_needed_loaded": 108,
"tn": 29690,
"fp": 108,
"tp": 156,
"unknown_loaded": 107,
"fn": 129
},
"precision": 0.5909090909090909,
"recall": 0.5473684210526316,
"f0.5": 0.5816554809843401,
"loads_per_turn": 0.8337078651685393,
"empty_turn_rate": 0.5348314606741573
},
{
"threshold": 0.8,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 307,
"empty": 261,
"needed_turns": 216,
"any_needed_loaded": 126,
"all_needed_loaded": 100,
"tn": 29720,
"fp": 78,
"tp": 142,
"unknown_loaded": 87,
"fn": 143
},
"precision": 0.6454545454545455,
"recall": 0.4982456140350877,
"f0.5": 0.6094420600858369,
"loads_per_turn": 0.6898876404494382,
"empty_turn_rate": 0.5865168539325842
},
{
"threshold": 0.85,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 267,
"empty": 278,
"needed_turns": 216,
"any_needed_loaded": 118,
"all_needed_loaded": 91,
"tn": 29734,
"fp": 64,
"tp": 131,
"unknown_loaded": 72,
"fn": 154
},
"precision": 0.6717948717948717,
"recall": 0.45964912280701753,
"f0.5": 0.6150234741784038,
"loads_per_turn": 0.6,
"empty_turn_rate": 0.6247191011235955
},
{
"threshold": 0.89,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 222,
"empty": 295,
"needed_turns": 216,
"any_needed_loaded": 104,
"all_needed_loaded": 78,
"tn": 29754,
"fp": 44,
"tp": 115,
"unknown_loaded": 63,
"fn": 170
},
"precision": 0.7232704402515723,
"recall": 0.40350877192982454,
"f0.5": 0.6243213897937026,
"loads_per_turn": 0.49887640449438203,
"empty_turn_rate": 0.6629213483146067
},
{
"threshold": 0.9,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 216,
"empty": 297,
"needed_turns": 216,
"any_needed_loaded": 101,
"all_needed_loaded": 75,
"tn": 29757,
"fp": 41,
"tp": 112,
"unknown_loaded": 63,
"fn": 173
},
"precision": 0.7320261437908496,
"recall": 0.3929824561403509,
"f0.5": 0.6243032329988851,
"loads_per_turn": 0.4853932584269663,
"empty_turn_rate": 0.6674157303370787
},
{
"threshold": 0.95,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 137,
"empty": 338,
"needed_turns": 216,
"any_needed_loaded": 77,
"all_needed_loaded": 53,
"tn": 29780,
"fp": 18,
"fn": 202,
"unknown_loaded": 36,
"tp": 83
},
"precision": 0.8217821782178217,
"recall": 0.2912280701754386,
"f0.5": 0.602322206095791,
"loads_per_turn": 0.30786516853932583,
"empty_turn_rate": 0.7595505617977528
},
{
"threshold": 0.97,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 85,
"empty": 374,
"needed_turns": 216,
"any_needed_loaded": 51,
"all_needed_loaded": 37,
"tn": 29788,
"fp": 10,
"fn": 231,
"unknown_loaded": 21,
"tp": 54
},
"precision": 0.84375,
"recall": 0.18947368421052632,
"f0.5": 0.49907578558225507,
"loads_per_turn": 0.19101123595505617,
"empty_turn_rate": 0.8404494382022472
},
{
"threshold": 0.99,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 12,
"empty": 433,
"needed_turns": 216,
"any_needed_loaded": 9,
"all_needed_loaded": 5,
"tn": 29798,
"fn": 276,
"unknown_loaded": 3,
"tp": 9
},
"precision": 1.0,
"recall": 0.031578947368421054,
"f0.5": 0.14018691588785046,
"loads_per_turn": 0.02696629213483146,
"empty_turn_rate": 0.9730337078651685
}
],
"called": [
{
"threshold": 0.5,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 639,
"empty": 176,
"needed_turns": 228,
"any_needed_loaded": 170,
"all_needed_loaded": 74,
"tn": 30152,
"fn": 280,
"fp": 395,
"tp": 244
},
"precision": 0.38184663536776214,
"recall": 0.46564885496183206,
"f0.5": 0.3961038961038961,
"loads_per_turn": 1.4359550561797754,
"empty_turn_rate": 0.3955056179775281
},
{
"threshold": 0.6,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 539,
"empty": 191,
"needed_turns": 228,
"any_needed_loaded": 165,
"all_needed_loaded": 68,
"tn": 30235,
"fn": 297,
"fp": 312,
"tp": 227
},
"precision": 0.42115027829313545,
"recall": 0.43320610687022904,
"f0.5": 0.42350746268656714,
"loads_per_turn": 1.2112359550561798,
"empty_turn_rate": 0.42921348314606744
},
{
"threshold": 0.7,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 429,
"empty": 222,
"needed_turns": 228,
"any_needed_loaded": 148,
"all_needed_loaded": 57,
"tn": 30312,
"fn": 330,
"fp": 235,
"tp": 194
},
"precision": 0.4522144522144522,
"recall": 0.3702290076335878,
"f0.5": 0.4330357142857143,
"loads_per_turn": 0.9640449438202248,
"empty_turn_rate": 0.49887640449438203
},
{
"threshold": 0.75,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 371,
"empty": 238,
"needed_turns": 228,
"any_needed_loaded": 141,
"all_needed_loaded": 51,
"tn": 30354,
"fn": 346,
"fp": 193,
"tp": 178
},
"precision": 0.4797843665768194,
"recall": 0.33969465648854963,
"f0.5": 0.44322709163346613,
"loads_per_turn": 0.8337078651685393,
"empty_turn_rate": 0.5348314606741573
},
{
"threshold": 0.8,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 307,
"empty": 261,
"needed_turns": 228,
"any_needed_loaded": 129,
"all_needed_loaded": 45,
"tn": 30395,
"fn": 369,
"fp": 152,
"tp": 155
},
"precision": 0.504885993485342,
"recall": 0.2958015267175573,
"f0.5": 0.442351598173516,
"loads_per_turn": 0.6898876404494382,
"empty_turn_rate": 0.5865168539325842
},
{
"threshold": 0.85,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 267,
"empty": 278,
"needed_turns": 228,
"any_needed_loaded": 116,
"all_needed_loaded": 36,
"tn": 30417,
"fn": 387,
"fp": 130,
"tp": 137
},
"precision": 0.5131086142322098,
"recall": 0.26145038167938933,
"f0.5": 0.43027638190954776,
"loads_per_turn": 0.6,
"empty_turn_rate": 0.6247191011235955
},
{
"threshold": 0.89,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 222,
"empty": 295,
"needed_turns": 228,
"any_needed_loaded": 105,
"all_needed_loaded": 31,
"tn": 30444,
"fn": 405,
"fp": 103,
"tp": 119
},
"precision": 0.536036036036036,
"recall": 0.22709923664122136,
"f0.5": 0.4213881019830028,
"loads_per_turn": 0.49887640449438203,
"empty_turn_rate": 0.6629213483146067
},
{
"threshold": 0.9,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 216,
"empty": 297,
"needed_turns": 228,
"any_needed_loaded": 103,
"all_needed_loaded": 31,
"tn": 30448,
"fn": 407,
"fp": 99,
"tp": 117
},
"precision": 0.5416666666666666,
"recall": 0.22328244274809161,
"f0.5": 0.4214697406340058,
"loads_per_turn": 0.4853932584269663,
"empty_turn_rate": 0.6674157303370787
},
{
"threshold": 0.95,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 137,
"empty": 338,
"needed_turns": 228,
"any_needed_loaded": 71,
"all_needed_loaded": 19,
"tn": 30485,
"fn": 449,
"fp": 62,
"tp": 75
},
"precision": 0.5474452554744526,
"recall": 0.1431297709923664,
"f0.5": 0.3498134328358209,
"loads_per_turn": 0.30786516853932583,
"empty_turn_rate": 0.7595505617977528
},
{
"threshold": 0.97,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 85,
"empty": 374,
"needed_turns": 228,
"any_needed_loaded": 45,
"all_needed_loaded": 11,
"tn": 30511,
"fn": 475,
"fp": 36,
"tp": 49
},
"precision": 0.5764705882352941,
"recall": 0.09351145038167939,
"f0.5": 0.2835648148148148,
"loads_per_turn": 0.19101123595505617,
"empty_turn_rate": 0.8404494382022472
},
{
"threshold": 0.99,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 12,
"empty": 433,
"needed_turns": 228,
"any_needed_loaded": 7,
"all_needed_loaded": 1,
"tn": 30542,
"fn": 517,
"fp": 5,
"tp": 7
},
"precision": 0.5833333333333334,
"recall": 0.013358778625954198,
"f0.5": 0.06118881118881119,
"loads_per_turn": 0.02696629213483146,
"empty_turn_rate": 0.9730337078651685
}
]
}
},
"B5-094": {
"original_report_sha256": "35c09c36938053b2eb285f4ca8700e2b61b0bb2ba96f1a63d1bbe2004e929bcf",
"input_sha256": {
"predictions": "e70357d58524a0714882aef5c5de98a6c4cf74a3ad82ae23ee1ed9f97789d1c0",
"rows": "67c4c86e3385f0241048f2633d97a4aad78a53a3b7a540592937a20eba669fd3",
"corpus": "c77abd8b40965c05cc43a7545e8c2db2405bdcfc18a73bad254632d523b67bcd"
},
"prediction_metadata_sha256": "de8a6974d1ca4a615f319089b2a6b023e5e57ede9bc03e52de5aa9524bde11c9",
"encoding": "independent",
"tool_option_words": 60,
"head_sha256": "550f30b94d5c6a8680d2cb2a607ebc9ee33e709c7679f72606d1e9fda17f2e90",
"truth": {
"consensus": [
{
"threshold": 0.95,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 137,
"empty": 338,
"needed_turns": 216,
"any_needed_loaded": 77,
"all_needed_loaded": 53,
"tn": 29780,
"fp": 18,
"fn": 202,
"unknown_loaded": 36,
"tp": 83
},
"precision": 0.8217821782178217,
"recall": 0.2912280701754386,
"f0.5": 0.602322206095791,
"loads_per_turn": 0.30786516853932583,
"empty_turn_rate": 0.7595505617977528
},
{
"threshold": 0.94,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 161,
"empty": 326,
"needed_turns": 216,
"any_needed_loaded": 83,
"all_needed_loaded": 58,
"tn": 29775,
"fp": 23,
"fn": 194,
"unknown_loaded": 47,
"tp": 91
},
"precision": 0.7982456140350878,
"recall": 0.3192982456140351,
"f0.5": 0.6140350877192983,
"loads_per_turn": 0.36179775280898874,
"empty_turn_rate": 0.7325842696629213
}
],
"called": [
{
"threshold": 0.95,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 137,
"empty": 338,
"needed_turns": 228,
"any_needed_loaded": 71,
"all_needed_loaded": 19,
"tn": 30485,
"fn": 449,
"fp": 62,
"tp": 75
},
"precision": 0.5474452554744526,
"recall": 0.1431297709923664,
"f0.5": 0.3498134328358209,
"loads_per_turn": 0.30786516853932583,
"empty_turn_rate": 0.7595505617977528
},
{
"threshold": 0.94,
"counts": {
"out_of_catalog_labels": 31,
"out_of_catalog_positives": 0,
"turns": 445,
"loads": 161,
"empty": 326,
"needed_turns": 228,
"any_needed_loaded": 83,
"all_needed_loaded": 21,
"tn": 30476,
"fn": 434,
"fp": 71,
"tp": 90
},
"precision": 0.5590062111801242,
"recall": 0.1717557251908397,
"f0.5": 0.3852739726027397,
"loads_per_turn": 0.36179775280898874,
"empty_turn_rate": 0.7325842696629213
}
]
}
}
}
}