Evidence record EV-0013

FAQ blocks and structured data showed no citation effect within a domain

An observational study of about 2 million AI-engine citations (preprint) found that FAQ blocks, structured data and Core Web Vitals had positive effects on citation in pooled data that reversed or fell to zero once domain fixed effects were applied.

Preprint · Null result · Retrieved

Evidence class: Preprint. Unreviewed. Many are by one author or a small team, and some authors have a stake in the result. Most AX research is in this class today. Pattern tags: discovery, measurement.

Effect, as the source reports it

  • Effect of the standard answer-engine checklist (FAQ blocks, structured data, Core Web Vitals) on citation frequency. Baseline: Pooled data: positive effects. With the change: With domain fixed effects: effects reverse or collapse to zero. Direction: no-change. Size: Reverse or zero within domain (Simpson's paradox). Sample: About 2 million citations; 10,000 pages from nineteen B2B SaaS workspaces; six months.
  • Prompt-content alignment as a predictor of citation. Direction: increase. Size: beta = +0.37, 95% CI [+0.33, +0.41]; the dominant page-level predictor. Sample: As above.
  • Domain-level AI authority versus the strongest non-alignment page feature. Direction: not-applicable. Size: About six times larger in mean absolute SHAP value. Sample: As above.

Agent profile

  • Models: ChatGPT, Claude, Google AI, Gemini.
  • Note on models: Four commercial answer engines, as products; model versions not stated in the abstract.
  • Run dates: Six months (dates not given in the abstract).

Conflicts of interest

None declared in the abstract. The data come from nineteen B2B SaaS workspaces and the abstract does not say who operates them; the full text was not checked.

Source

What Drives Citations in Production Large Language Models? An Observational Multi-Method Study of Two Million AI Citations Across Ten Thousand Web Pages, arXiv, Ben Moore, Liam Dunne, 28 September 2026, arXiv:2609.35077. Retrieved ; verification: abstract-only.

Every number in this record was checked against the live arXiv abstract page on 2026-10-08. The full text was not re-checked.

Limitations

  • Preprint, not peer reviewed.
  • Observational; causal claims are limited.
  • B2B SaaS pages only.
  • Measures citation, not agent task success.

For designers

Adding FAQ markup or structured data is not, on this evidence, a reliable way to get cited by answer engines. Content that matches what people actually ask carried far more signal.

Cite this record

Cite the original source for any number, and keep the evidence class and model set with the figure. To point at this record, use "AX evidence register, EV-0013" and this page's address, https://agentexperience.tech/evidence/ev-0013/. The record is also in /evidence.json. The register's licence will be confirmed before its source repository is published.