yogsoth-ai Confidence Scoring
Assign calibrated confidence scores to causal claims.
Tool
CC file edit
Protocol
- Count supporting evidence (weighted by evidence hierarchy)
- Count contradicting evidence (weighted similarly)
- Calculate net confidence: support_weight / (support_weight + contradict_weight)
- Adjust for mechanism plausibility (+0.1 if strong mechanism, -0.1 if no mechanism)
- Update claim page frontmatter confidence field
HARD-GATE
Yield
Returns: { claim: string, confidence: number, evidence_count: number }