{"slug":"brycewang-stanford-aistats-experiments","source_name":"brycewang-stanford/aistats-experiments","name":"Brycewang Stanford/Aistats Experiments","description":"Use when designing or auditing AISTATS experiments, simulations, baselines, statistical tests, uncertainty estimates, ablations, random seeds, hyperparameters, compute, dataset handling, and claim-to-evidence fit, with emphasis on experiments that validate theorems rather than chase leaderboards.","version":1,"lift":{"pass_rate_delta_pts":17.39,"pass_rate_pct":91.3,"total_cases":23,"passed_cases":21,"tokens_delta_pct":-4.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T04:23:21.470907+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":17.39,"with_pass_pct":91.3,"without_pass_pct":73.9,"tokens_delta_pct":-4.1,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-15T04:23:21.470907+00:00","run_id":"9e06541e-d556-493b-a495-3cc6cde1a86c","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":"1a535861c41504ea1c35341d4a76a7f673cb4d4ae918a4b614043fca8c34a8f2","raw_url":"https://app.decimal.ai/s/brycewang-stanford-aistats-experiments/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-aistats-experiments"}