{"slug":"tangxiangru-math-equal-effort-baselines-and-knob-sweeps","source_name":"tangxiangru/math-equal-effort-baselines-and-knob-sweeps","name":"Tangxiangru/Math Equal Effort Baselines And Knob Sweeps","description":"Use at study design when the source names competing algorithms and they are about to become a related-work paragraph instead of arms. Covers running every named baseline at equal tuning effort, and sweeping the parameter you claim credit for.","version":1,"lift":{"pass_rate_delta_pts":77.27,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":20.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-25T12:20:54.605576+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":77.27,"with_pass_pct":95.5,"without_pass_pct":18.2,"tokens_delta_pct":20.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-25T12:20:54.605576+00:00","run_id":"c7764637-e372-43d7-8bbf-acb4fff12815","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":"NOASSERTION","install_count":0,"manifest_hash":"7c7a2d67a06f12e91e00a3aab057b1c9a80963c82eea883cd44f238df8760dc8","raw_url":"https://app.decimal.ai/s/tangxiangru-math-equal-effort-baselines-and-knob-sweeps/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/tangxiangru-math-equal-effort-baselines-and-knob-sweeps"}