{"version":1,"run_id":"run_b40a4cca1b","files":[{"name":"launch-instructions-a43b123dc830.md","kind":"instructions","sha256":"a43b123dc830f9e630619639702ede1e853ac487eafe31b58d6b79b1c4434e8f","size":32010,"url":"/api/runs/run_b40a4cca1b/evidence/a43b123dc830f9e630619639702ede1e853ac487eafe31b58d6b79b1c4434e8f"},{"name":"launch-instructions.md","kind":"instructions","sha256":"a43b123dc830f9e630619639702ede1e853ac487eafe31b58d6b79b1c4434e8f","size":32010,"url":"/api/runs/run_b40a4cca1b/evidence/a43b123dc830f9e630619639702ede1e853ac487eafe31b58d6b79b1c4434e8f"},{"name":"rl_score_centering.py","kind":"script","sha256":"388f91b33c1a648ebed6cd1ec0223dde89829aa5c106dc505114ee53c3c942c6","size":9833,"url":"/api/runs/run_b40a4cca1b/evidence/388f91b33c1a648ebed6cd1ec0223dde89829aa5c106dc505114ee53c3c942c6"},{"name":"gsm8k_eval.py","kind":"script","sha256":"1c26e3c71f3af5ccf1122a88aafa9c8f208c9a3308be44a45a790459a2761d16","size":4356,"url":"/api/runs/run_b40a4cca1b/evidence/1c26e3c71f3af5ccf1122a88aafa9c8f208c9a3308be44a45a790459a2761d16"},{"name":"preflight2.py","kind":"script","sha256":"d924f6390c0b058aa2ee6ad50546e62c762b10c8285b8962df28077d556e5705","size":4950,"url":"/api/runs/run_b40a4cca1b/evidence/d924f6390c0b058aa2ee6ad50546e62c762b10c8285b8962df28077d556e5705"},{"name":"ref_parity.py","kind":"script","sha256":"834e424488d647724c3028906a41f3954634cc60f5190b281e02975fb23bad34","size":4772,"url":"/api/runs/run_b40a4cca1b/evidence/834e424488d647724c3028906a41f3954634cc60f5190b281e02975fb23bad34"},{"name":"pilot.py","kind":"script","sha256":"7f88b0bede92390b9c49850fadde0c7d4f8a531ef1ecf87469ef09bb07d2ac5c","size":565,"url":"/api/runs/run_b40a4cca1b/evidence/7f88b0bede92390b9c49850fadde0c7d4f8a531ef1ecf87469ef09bb07d2ac5c"},{"name":"common.py","kind":"script","sha256":"69661150722db2a12020f5a2f73de6247462fbb82feb6b8cbd17eb5b2108543e","size":291,"url":"/api/runs/run_b40a4cca1b/evidence/69661150722db2a12020f5a2f73de6247462fbb82feb6b8cbd17eb5b2108543e"},{"name":"effective-config.json","kind":"effective_config","sha256":"89615187d8fe7c902a0234f962565b38de7aa507afcf52f67d69d40f294f834f","size":1333,"url":"/api/runs/run_b40a4cca1b/evidence/89615187d8fe7c902a0234f962565b38de7aa507afcf52f67d69d40f294f834f"},{"name":"code_revision.json","kind":"code_revision","sha256":"614b48ad7ab1dea23aee1f6e7b4f65f3a47b030246a9b4aa05cd90e15f5dd771","size":1125,"url":"/api/runs/run_b40a4cca1b/evidence/614b48ad7ab1dea23aee1f6e7b4f65f3a47b030246a9b4aa05cd90e15f5dd771"},{"name":"sc_nonfinite_fix.patch","kind":"code_patch","sha256":"65a4c3080f130e688139bb7ad1353f15a8025f56d756ef94948d3fde48ed56b6","size":677,"url":"/api/runs/run_b40a4cca1b/evidence/65a4c3080f130e688139bb7ad1353f15a8025f56d756ef94948d3fde48ed56b6"},{"name":"preflight_result.json","kind":"metrics","sha256":"811ead4861449a7fbc3e052f942678a998e546b1ebf61720447d4f68964b011e","size":4033,"url":"/api/runs/run_b40a4cca1b/evidence/811ead4861449a7fbc3e052f942678a998e546b1ebf61720447d4f68964b011e"},{"name":"ref_parity_result_v2.json","kind":"metrics","sha256":"2c564c3010f569b9382cc958f77379acc608b2fb4884f5da246ddc8b1139533d","size":1774,"url":"/api/runs/run_b40a4cca1b/evidence/2c564c3010f569b9382cc958f77379acc608b2fb4884f5da246ddc8b1139533d"},{"name":"correctness_preflight.json","kind":"metrics","sha256":"c5257497b1693669f5a5816fcc83e7e143fbac15cc1ceaed4391227bac7d7bbe","size":3390,"url":"/api/runs/run_b40a4cca1b/evidence/c5257497b1693669f5a5816fcc83e7e143fbac15cc1ceaed4391227bac7d7bbe"},{"name":"proposed_correctness_plan.json","kind":"metrics","sha256":"9e9bdee20fe549b5f284fd8f564ba47fd645832fa635f1ce083b5e763ecb6cfc","size":837,"url":"/api/runs/run_b40a4cca1b/evidence/9e9bdee20fe549b5f284fd8f564ba47fd645832fa635f1ce083b5e763ecb6cfc"},{"name":"spec_effective_with_proposed_plan.json","kind":"metrics","sha256":"4d9bfb4f605d9a2e0a74c6ed2cf5d46f485a254fe48394da1c44bd4459eea4cf","size":3922,"url":"/api/runs/run_b40a4cca1b/evidence/4d9bfb4f605d9a2e0a74c6ed2cf5d46f485a254fe48394da1c44bd4459eea4cf"}],"checkpoints":[],"per_arm_metrics":{"base":{"accuracy":0.684}},"missing":["predictions","checkpoint_references"],"errors":["file 11: attachment retrieval returned HTTP 401","file 17: invalid file name or kind","file 18: invalid file name or kind","file 19: attachment retrieval returned HTTP 401","file 20: invalid file name or kind","file 21: invalid file name or kind","file 22: attachment retrieval returned HTTP 401"],"status":"partial"}