Entity Density and Content Structure as Independent Levers on AI Citation Under Forced Retrieval: A Preregistration

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.