{"slug":"brycewang-stanford-aaai-experiments","source_name":"brycewang-stanford/aaai-experiments","name":"Brycewang Stanford/Aaai Experiments","description":"Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":45.5,"total_cases":22,"passed_cases":10,"tokens_delta_pct":15.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-14T19:08:32.628447+00:00"},"skill_score":0.4545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":45.5,"without_pass_pct":18.2,"tokens_delta_pct":15.5,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-14T19:08:32.628447+00:00","run_id":"60165261-d59a-4551-8e34-79e2ed617083","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":"72c3d10b27c2198791c83cd566d1b1f660eedba0cbfc390003ff15ea6ec228c3","raw_url":"https://app.decimal.ai/s/brycewang-stanford-aaai-experiments/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-aaai-experiments"}