Validate & govern

Benchmark first

Corpora: FEVER · FEVEROUS · ContraDoc · FreshQA

Protocol: Report verdict macro-F1 and accuracy separately from evidence precision/recall/F1 and contradiction localization. Pin corpus and source revisions. Replay corrections and removals, then measure stale-answer rate, time-to-consistency, unsupported-answer rate, and authorization leakage. A correct label without the complete evidence set does not pass the evidence contract.

• Document-level self-contradiction detection
• Evidence contracts
• Freshness and impact
• Reviewed workflows and cached answers
• Verification portfolios
• Errors and deliberate boundaries