{"slug":"brycewang-stanford-cav-reproducibility","source_name":"brycewang-stanford/cav-reproducibility","name":"Brycewang Stanford/Cav Reproducibility","description":"Use when strengthening CAV (Computer Aided Verification) reproducibility, covering benchmark provenance (SV-COMP/SMT-COMP/HWMCC/VNN-COMP set revisions), pinned tool and baseline versions, resource limits and hardware, seeds for randomized/portfolio solvers, checkable proof witnesses/certificates for soundness claims, and consistency between the paper's tables and the artifact.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":7.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T20:39:10.018272+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":81.8,"without_pass_pct":54.5,"tokens_delta_pct":7.5,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-15T20:39:10.018272+00:00","run_id":"c44e7d75-16b8-4973-821f-f728106aea9a","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":"e3c70d20ec20aac32ab1c9be8f40762381ae8d5ae70ad3cb4a72daf299189668","raw_url":"https://app.decimal.ai/s/brycewang-stanford-cav-reproducibility/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-cav-reproducibility"}