{"slug":"brycewang-stanford-aamas-artifact-evaluation","source_name":"brycewang-stanford/aamas-artifact-evaluation","name":"Brycewang Stanford/Aamas Artifact Evaluation","description":"Use when packaging AAMAS multiagent code, environments, opponent and population sets, random seeds, game definitions, and logs as anonymous supplementary evidence or a public post-acceptance release, even without a separate artifact badge, so that game-theory and MARL reviewers can inspect and re-run the interaction claims.","version":1,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":-4.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T03:01:55.108337+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":95.5,"without_pass_pct":59.1,"tokens_delta_pct":-4.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-15T03:01:55.108337+00:00","run_id":"be98da3d-9175-4466-8665-15b952a1bea9","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":"35bd4b1f1fdcbac80c07fdc5715467650f3be65ba1d7867a3bb9c185366a762d","raw_url":"https://app.decimal.ai/s/brycewang-stanford-aamas-artifact-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-aamas-artifact-evaluation"}