{"slug":"yogsoth-ai-reproducibility-third-party-verification","source_name":"yogsoth-ai/reproducibility-third-party-verification","name":"Yogsoth AI/Reproducibility Third Party Verification","description":"(Proposal, unverified) Attempt to verify a paper's reported results by actually executing its released code/scripts against its own reported configuration — the only SOP in this package whose action type is code execution rather than text reading/judgment. Use this after unit-classification has extracted the paper's reported configuration/hyperparameters as classified units; \"not_attempted\" is a correct, common output when the paper's own reporting is too incomplete to run, not a failure of this","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":72.7,"total_cases":22,"passed_cases":16,"tokens_delta_pct":-10.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-07T11:04:18.915733+00:00"},"skill_score":0.7273,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":72.7,"without_pass_pct":31.8,"tokens_delta_pct":-10.6,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-07T11:04:18.915733+00:00","run_id":"3997363a-4df6-4832-b215-59543c8ca651","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":"Apache-2.0","install_count":0,"manifest_hash":"7120223fb586f6ad073c94b908d8fd86ff0349c6b1afebe93246a46d4d4518e4","raw_url":"https://app.decimal.ai/s/yogsoth-ai-reproducibility-third-party-verification/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/yogsoth-ai-reproducibility-third-party-verification"}