{"version":1,"run_id":"run_0f5f08aaaa","files":[{"name":"generation_audit_v3.json","kind":"generated_audit","sha256":"7fe5e5322a2fc54d01ef7d33df13bdd47bbe51e91dd87a56afdcad7ef0f694ea","size":456,"url":"/api/runs/run_0f5f08aaaa/evidence/7fe5e5322a2fc54d01ef7d33df13bdd47bbe51e91dd87a56afdcad7ef0f694ea"},{"name":"effective-config.json","kind":"effective_config","sha256":"9cca260f3eb46eac623f65e86ad62a50e4113fb0ce4314689fcc6d9257311d46","size":357,"url":"/api/runs/run_0f5f08aaaa/evidence/9cca260f3eb46eac623f65e86ad62a50e4113fb0ce4314689fcc6d9257311d46"},{"name":"code-revision.txt","kind":"code_revision","sha256":"747d84f06cd282a905c8b4f586a3226909f209919aee422b6df23a704d9a30a4","size":405,"url":"/api/runs/run_0f5f08aaaa/evidence/747d84f06cd282a905c8b4f586a3226909f209919aee422b6df23a704d9a30a4"}],"checkpoints":[{"arm":"gsm8k","uri":"tinker://7930b93123356fc28cbdfbfd3d1aecb3:train:0/sampler_weights/000025","step":25},{"arm":"selfgen","uri":"tinker://b07dfb09801476f40e8554db314560fc:train:0/sampler_weights/000025","step":25}],"per_arm_metrics":{"base":{"accuracy":0.29946929492039426},"gsm8k":{"accuracy":0.909021986353298},"selfgen":{"accuracy":0.9014404852160728}},"missing":["script","predictions"],"errors":["file 1: file name already used; use a new name for new evidence"],"status":"partial"}