{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/judge-ai-confidence-by-whether-it-separates-right-from-wrong",
  "id": "MHC-D-RESEARCH-0493",
  "version": "0.1.0",
  "title": "Judge AI confidence by whether it separates right from wrong",
  "summary": "A confidence score is useful when it knows which answers deserve confidence.",
  "kind": "principle",
  "body": "Evaluate whether higher AI confidence actually corresponds to more correct outputs and lower confidence to more errors. This discrimination—metacognitive sensitivity—is different from the model simply sounding or scoring confidently. Use a labeled task set before letting confidence drive routing or human reliance.",
  "limits": [
    "Metacognitive sensitivity can drift when data, model or prompts change; revalidate it over time."
  ],
  "topics": [
    "union-ai-reliance-metacognition"
  ],
  "intents": [],
  "source_ids": [
    "RS-45C4F121413B315D"
  ],
  "evidence": [
    {
      "claim": "Metacognitive sensitivity concerns how well confidence distinguishes correct from incorrect decisions, which is different from average confidence or simple calibration.",
      "source_id": "RS-45C4F121413B315D",
      "role": "supports",
      "note": "Formal metacognitive metrics require enough labeled decisions; a single confidence value cannot establish sensitivity.",
      "locator": "Abstract and theoretical model"
    }
  ],
  "use_when": [
    "A system reports confidence scores and the team treats high average confidence as evidence of useful uncertainty."
  ],
  "avoid_when": [
    "Metacognitive sensitivity can drift when data, model or prompts change; revalidate it over time."
  ],
  "example": "If an extraction model gives 95% confidence to both correct and wrong tax IDs, the confidence field is not useful for selective review.",
  "check": "Higher confidence demonstrably separates more reliable outputs from less reliable ones on the relevant task class.",
  "sources": [
    {
      "id": "RS-45C4F121413B315D",
      "title": "Modeling the joint impact of human and AI metacognitive sensitivity on human-AI collaboration",
      "url": "https://www.sciencedirect.com/science/article/pii/S0022249626000192"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0493",
      "to": "MHC-D-RESEARCH-0494",
      "type": "use_before",
      "url": "/knowledge/do-not-expose-ai-confidence-until-you-have-tested-its-calibration"
    }
  ],
  "collections": [
    {
      "id": "RC-39B535F35706B375",
      "title": "Calibrate when to rely on AI instead of measuring trust as a feeling",
      "url": "/collections/calibrate-when-to-rely-on-ai-instead-of-measuring-trust-as-a-feeling"
    }
  ]
}