{"slug":"brycewang-stanford-corl-experiments","source_name":"brycewang-stanford/corl-experiments","name":"Brycewang Stanford/Corl Experiments","description":"Use when designing or auditing experiments for a CoRL robot-learning paper — seeds and evaluation-episode counts, task-suite breadth, real-robot versus simulation evidence, sim-to-real gap measurement, baseline fairness across BC/RL/VLA families, generalization splits, and statistics for success-rate claims.","version":1,"lift":{"pass_rate_delta_pts":22.73,"pass_rate_pct":77.3,"total_cases":22,"passed_cases":17,"tokens_delta_pct":50.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-01T20:33:56.795473+00:00"},"skill_score":0.7727,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":22.73,"with_pass_pct":77.3,"without_pass_pct":54.5,"tokens_delta_pct":50.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-01T20:33:56.795473+00:00","run_id":"b06fd287-91ab-49e7-815a-33770c11bf58","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":"be638e29bafff854df60efc7a67c173854cc0a30c35b8555bdf2b5c51efe981b","raw_url":"https://app.decimal.ai/s/brycewang-stanford-corl-experiments/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-corl-experiments"}