{"slug":"brycewang-stanford-colm-artifact-evaluation","source_name":"brycewang-stanford/colm-artifact-evaluation","name":"Brycewang Stanford/Colm Artifact Evaluation","description":"Use when packaging the artifacts of a COLM paper — model weights, training data, prompts, evaluation sets, and cached model outputs — for anonymous review and public post-acceptance release, navigating licenses, API terms-of-service limits, and the absence of a formal COLM artifact track.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":100,"total_cases":22,"passed_cases":22,"tokens_delta_pct":37.1,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-31T04:38:43.046826+00:00"},"skill_score":1,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":100,"without_pass_pct":72.7,"tokens_delta_pct":37.1,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-31T04:38:43.046826+00:00","run_id":"8bd6b51f-9666-4f1c-b2cd-7ad6de8a253a","latest_attempt":{"id":"8bd6b51f-9666-4f1c-b2cd-7ad6de8a253a","runner_model":"gemini-3.6-flash","overall_verdict":"pass","completed_at":"2026-08-31T04:38:43.046826+00:00","gate":null},"version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"b0cfb5199c4b6be543bd1fc4bd75a1b2decff6bfd1069f6e9061133437a53985","install_name":"brycewang-stanford-colm-artifact-evaluation","version_id":"8e11c52c-41ca-4792-a3bb-290dfb3f0b5a","body_sha256":"b0cfb5199c4b6be543bd1fc4bd75a1b2decff6bfd1069f6e9061133437a53985","render_hash":"cac7a8ab04d78990447799b2017067b92a458f774292076f6d281ad52e85e1ff","raw_url":"https://app.decimal.ai/s/brycewang-stanford-colm-artifact-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-colm-artifact-evaluation"}