Preregistered protocol tests the influence of entity density and content structure on AI citations, suggesting significant factors in AI performance.
A preregistered protocol (no results) testing whether entity density and content structure independently affect AI-engine citation under forced retrieval, across ChatGPT, Claude, Perplexity and Gemini answer-time agents. Registered before confirmatory data collection. Includes a 2x2 design, a synthetic control entity, binary citation scoring, a conservative noise threshold, an independent verification subset, and a declared competing interest.
No takes yet. Share an insight, caveat, or question.
Ferreira et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: