{"slug":"openmatter-network-ai-reliability","source_name":"openmatter-network/ai-reliability","name":"Openmatter Network/AI Reliability","description":"Use when evaluating the reliability (score consistency/stability) of an AI/ML selection tool — Concern 6 of Tippins, Oswald & McPhail (2021). Covers reliability as an absolute requirement, what stability means for AI scores, evidence that machine scoring can be as or more reliable than human scoring, the questionable reliability of facial-emotion analysis (including across skin tone, disability, and altered features), and confounds from individual differences in the data generated (e.g., extrave","version":1,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":36,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T14:09:37.382810+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":90.9,"without_pass_pct":77.3,"tokens_delta_pct":36,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-03T14:09:37.382810+00:00","run_id":"1f66e60c-7a6e-4375-8dea-96ceb538769c","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":"fd0c55552a4cffa6ddc0daee1a9223a9acde1f38e84e9390cacde7cdefa01279","raw_url":"https://app.decimal.ai/s/openmatter-network-ai-reliability/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/openmatter-network-ai-reliability"}