How low domain overlap reveals separate retrieval ecosystems—and why a citation win rarely transfers automatically.
Low cross-platform overlap is a recurring finding
Multiple audits show different AI surfaces retrieving different domains for the same information need. Martinez summarizes a Google-focused study where URL-level Jaccard similarity among organic Google, AI Overviews, and Gemini was only about 0.11–0.18.
Cross-model overlap can be even smaller
Chen and colleagues reported automotive domain overlap of 0.147 for Claude–GPT, 0.251 for Claude–Perplexity, and 0.096 for GPT–Perplexity. Consumer-electronics pairs ranged from about 0.088 to 0.200.
These values belong to specific experiments, but they show substantial ecology divergence.
Jaccard similarity makes overlap explicit
For two domain sets, divide their intersection by their union. Report both the score and the underlying set sizes so a small shared core is not mistaken for broad agreement.
A citation win is not automatically transferable
A source visible on one engine may be absent on another because retrieval providers, source pools, selection, and context differ. Dashboards must specify engine and surface rather than reporting a single “AI rank.”
Measure Brand × Prompt × Engine × Run—not Brand × Prompt alone.
Questions about this topic
What is cross-engine source overlap?+
The degree to which two engines retrieve or cite the same domains or URLs for comparable prompts.
How is Jaccard similarity calculated?+
Divide the number of shared sources by the number of unique sources in the combined sets.
Does success on one engine transfer to another?+
Not reliably. Engines may use materially different source ecosystems.
What is domain diversity?+
The breadth of distinct domains contributing evidence within an engine, prompt family, or dataset.
References
Sources are listed in APA 7 style. Preprints are identified as such and should not be treated as peer-reviewed findings unless separately published.
- Martinez, O. (2026). Optimizing visibility in generative engines: A critical survey of generative engine optimization (2023–2026) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2607.14035
- Chen, M., Wang, X., Chen, K., & Koudas, N. (2025). Generative engine optimization: How to dominate AI search [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2509.08919
- Zhang, K., He, X., & Yao, J. (2026). From citation selection to citation absorption: A measurement framework for generative engine optimization across AI search platforms [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2604.25707