{"slug":"brycewang-stanford-corl-artifact-evaluation","source_name":"brycewang-stanford/corl-artifact-evaluation","name":"Brycewang Stanford/Corl Artifact Evaluation","description":"Use when packaging the artifacts of a CoRL paper — code, training configs, demonstration datasets, policy checkpoints, simulation environments, and benchmark definitions — as anonymous review-time evidence and as durable public releases after acceptance, in a venue with no formal artifact-badging track.","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":18,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-01T20:22:27.928143+00:00"},"skill_score":0.8636,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":86.4,"without_pass_pct":45.5,"tokens_delta_pct":18,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-01T20:22:27.928143+00:00","run_id":"da307be8-dcf3-44f7-bdfd-04db636a145d","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,"manifest_hash":"625c101395295197b192418323d9de51ad4be4f136cd8fddafa6f027aa826e20","raw_url":"https://app.decimal.ai/s/brycewang-stanford-corl-artifact-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-corl-artifact-evaluation"}