{"adapter":{"adapter_identity":"MERGED_FULL_WEIGHTS_NO_LORA","adapter_path":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-THINK/out/O7B-THINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/2d7e9e7d85c88ad60cd12df874fd903f00c017cffe9990a8c6fb5f444642dbf3/step-000904-tokens-63378772/adapter","adapter_tree_sha256":"fe68ff152a282e7ce3e0a14738544921a839b859686c47a1a2593b7e3b8893c4","checkpoint":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-THINK/out/O7B-THINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/2d7e9e7d85c88ad60cd12df874fd903f00c017cffe9990a8c6fb5f444642dbf3/step-000904-tokens-63378772","checkpoint_manifest_sha256":"42a14a7b08216555ed6f8d720039289212cc0607dfbcc7c9afefd8ad668411e4","merged_path":"/workspace/code-sft-runs/rstar-eval/official-dev256/v4-o7b-think/scratch/step-000904-tokens-63378772-merged-full"},"arm":"official-v4-o7b-think","base":false,"benchmark_contract":{"date_filter":null,"native_index":{"bytes":2546647101,"immutable_object_uri":"r2mtx:mxx/isolated-backups/full-workspace/20260826T031752Z-8bcbe83efc6607702f6b681b4429d72dc6c1a4c570f18c85e8c7cee5743c682a/objects/sha256/ea/ea66e0d8814490a7e0d7ff555297e43a7d9662405c16609f9df51b42ec1b1cc1","path":"/workspace/code-sft-runs/rstar-eval/contracts/dev256/native_index.jsonl","sha256":"ea66e0d8814490a7e0d7ff555297e43a7d9662405c16609f9df51b42ec1b1cc1"},"ordered_task_ids_sha256":"8f4b14d4af19399ed59a052ef970ad18eb83f19cc5257bcafa4fafd1938315b9","prompts":{"path":"/workspace/code-sft-runs/rstar-eval/contracts/dev256/evalscope_prompts.jsonl","sha256":"b8c2047bf804c01a1cc82d16e07599dea0f4d94a42af6a26386c832a33747695"},"recovery":{"path":"/workspace/code-sft-runs/rstar-eval/contracts/dev256/RECOVERY.json","sha256":"011d8adba4986651a5d83add11626f155270008c9e69e89a4a86e753d71b0906"},"role":"DIAGNOSTIC_ONLY","rows":256,"schema":"CTX_LCDIV_DEV256_RECOVERY_V2","seed":3407,"seed_count":1,"subset_filter":null,"universe_rule":"exact content-addressed ordered task IDs recovered from six frozen test*.jsonl shards; no resampling, shuffle, date filtering, subset filtering, or hub refresh"},"cap_rate":0.58203125,"caps":149,"checkpoint":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-THINK/out/O7B-THINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/2d7e9e7d85c88ad60cd12df874fd903f00c017cffe9990a8c6fb5f444642dbf3/step-000904-tokens-63378772","code_plus_stop":56,"first_stop_accounted":256,"first_stop_token":{"100257":0,"100265":0,"151643":0,"151645":0,"length":149,"other":107},"gpu":2,"kind":"merged_full_weights","lora":false,"merged":"/workspace/code-sft-runs/rstar-eval/official-dev256/v4-o7b-think/scratch/step-000904-tokens-63378772-merged-full","mode":"think","native_validation":{"modes":{"functional":109,"stdin":147},"native_index_sha256":"ea66e0d8814490a7e0d7ff555297e43a7d9662405c16609f9df51b42ec1b1cc1","ordered_evaluation_samples_sha256":"811cc4cd88b1863ab973be0b906c12934f1acc67d436f1b48d4a6863f7e0a4c7","ordered_task_ids_sha256":"8f4b14d4af19399ed59a052ef970ad18eb83f19cc5257bcafa4fafd1938315b9","rows":256},"pass_at_1":0.21875,"passed":56,"pending_infra":0,"per_item":{"document_sha256":"7c70c8631d732e8bbebc7b6d207df8ee4f31c873acef7011b3ec19ded2f8d25f","path":"/workspace/code-sft-runs/rstar-eval/official-dev256/v4-o7b-think/results/PER_ITEM.json","sha256":"09b2d195750b6e01d4433b3b8c22f2081e4c6427e9e9327d27debc26e8d98b10"},"port":18612,"protocol_failure":0,"queue_sha256":"80a75fca2a228428ecac539eb773958b8c38975d9adb727093548aefa27fa39b","receipt_sha256":"b249bf8359d23668a39d3746277499d1fb0305c01c4156cb00666c6a5b36d205","renderer_authority":{"path":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/tokenizers/olmo3-lcb-noprefill.authority.json","sha256":"162967ab55d8cd97f7756069d044bad3aa654faa1dc20e02aeb4bbb91bf1659a"},"renderer_id":"olmo3-lcb-noprefill","rows":256,"runner":{"evalscope_adapter_sha256":"6c4977439b751003d6900c5cec2e7b3244599d3427903f99e3d7300d2c0d7687","evalscope_core_files":{"evaluate_utils.py":"a16167430f636906d15c6540f4640bb72973d9c34cea87928ebe870b51fc9794","extract_utils.py":"1c74c40a9250191cdaa5560104df583a4bec493154a2ea3eb603c35237c2a038","load_utils.py":"7c4cd6cff7d41b08b935cba6e4f35517d8c572e0f01a0b3b56dff5d182811364","testing_util.py":"72ac3f87e288cf39ed882e6f31cfc1192e5027d97d7d9a7730e2aa946effa329"},"evalscope_sandbox_sha256":"fcbbd6ec7634225ce023da194d178206ef778ad8e945e0ac36353934c09186f0","evalscope_version":"1.11.0","library_sha256":"0ab605fc8f758b1507752f19b4266c0a17e562774b1dcbe8e138708fd76ad7df","official_task":{"base":false,"cache_root":"/workspace/code-sft-runs/rstar-eval/official-dev256/v4-o7b-think/cache","checkpoint":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-THINK/out/O7B-THINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/2d7e9e7d85c88ad60cd12df874fd903f00c017cffe9990a8c6fb5f444642dbf3/step-000904-tokens-63378772","label":"v4-o7b-think","mode":"think","student_family":"olmo"},"runner_id":"code-sft-rstar-lcb-handoff-v2","runner_sha256":"5ea2f032337a72c97f0c8cda2310e9f99e649f2bbe8cbcea8e2bcbd5072c6431","sandbox_runtime":{"execution_module_sha256":"cb162f70bb548694ad08372c71399b9011500b198cc7d23bf5dc2f95912189fc","pool_config_sha256":"33de3626e6591d5dcb0b1b99bb8fa53b05acd42a8a9fe65637e2fd2c890b0790","pool_probe_sha256":"6b2a91c4f5ff066ca9617602d166f4e19a9d5228a990ea2aa62b6fd76959ebc0","scope_lease":"CODE_SFT_SANDBOX_SCOPE_LEASE_V1","scope_module_sha256":"d5c0cb716af86aa2bc03c12cce8106046692672eafe6fb7cc7562e4c9752a8bf","transport":"SANDBOX_API_V1_DIRECT_TOOL_EXECUTE"}},"schema":"CODE_SFT_RSTAR_EVAL_SUITE_RECEIPT_V1","scored":256,"seed":3407,"served_model":"v4-o7b-think-dev256","status":"COMPLETE","student_family":"olmo","suite":"dev256","unscored":0}