Original research · Pre-registered RCT

Does schema markup increase AI citations?

The single most contested tactic in GEO, and the only one where the strongest existing evidence is a null result. This page registers a randomized test to settle it.

Ahrefs' observational test on 1,885 pages found citations 'barely moved' after adding schema. Nobody has run a randomized version. This is that study's design, published before a single page is enrolled.

Ritik Namdev Ritik Namdev ·Published September 2026 ·v0 — recruiting participant sites ·12 min read
The short version

This is not a results page — it's a pre-registration. No pages have been enrolled yet. We're publishing the design first, including the hypothesis and what would count as disconfirming evidence, so the result — whichever way it comes out — is trustworthy rather than reverse-engineered from a convenient finding.

Why this needs an RCT, not another observational test

The existing evidence on schema and AI citation is genuinely mixed. Both sides of the debate can point to something real. What neither side has is a randomized test: one where whether a page gets schema is decided by a coin flip, not by which site owners happened to add it. Without randomization, any observed difference, or lack of one, is confounded. Sites that invest in schema also tend to invest in content quality, technical SEO, and backlinks. Any of those could independently move citation rate.

A brief history of the schema debate

Schema markup has been a settled, well-evidenced recommendation for classic Google search for years. Structured data reliably improves rich-result eligibility, and in many documented cases, click-through rate on traditional SERPs. That established track record is likely a major reason the recommendation carried over so readily into GEO advice. If schema helps Google understand a page, the reasoning goes, it should help an AI system too.

The direct-fetch evidence complicating that assumption, AI systems apparently reading only visible HTML, is comparatively recent. It hasn't yet displaced the inherited assumption in most published GEO guidance. That's exactly the gap this study is designed to close, with a genuinely new, dedicated test rather than borrowed classic-SEO precedent.

The evidence so far

Evidence

Ahrefs tracked 1,885 pages that added schema markup and found AI citations "barely moved" — a real, disclosed observational test, the strongest public evidence available today.

Evidence

Separate live-fetch tests across five major AI systems found none of them used information present only in JSON-LD — every system extracted visible HTML content only during direct retrieval.

Hypothesis

Counter-argument: schema may still play a role in indexing or retrieval stages that happen before a live fetch — not ruled out, only the direct-fetch mechanism has been tested.

Study design

RCT collection pipeline
  1. 01 Recruit 400 pages Matched pairs, similar topic/authority
  2. 02 Randomize Half get schema added, half don't
  3. 03 Wait one cycle Full Index collection window
  4. 04 Measure citation rate Treatment vs. control, both arms
  5. 05 Publish either result Positive or null, pre-committed

The registered hypothesis

H0 (null, our prediction): Adding schema markup to a page produces no statistically detectable change in AI citation rate, holding topic, content, and existing authority constant.

H1 (alternative): Adding schema markup causally increases AI citation rate by a detectable margin.

We are registering our prediction as the null (H0) — consistent with the observational evidence and the live-fetch findings — specifically so a positive result, if it occurs, will be a genuinely surprising finding rather than confirmation of something we already expected.

We're registering our prediction for the schema RCT as the null hypothesis — that schema won't move AI citation rate. If we're wrong, that's the more interesting result, and we've committed to publishing it either way.

Share on X

Variables measured

TreatmentAdding Article/Product/FAQ schema (matched to page type) where none existed before.
ControlMatched pages, no schema change, otherwise identical monitoring.
Primary outcomeCitation rate across the Index's seven tracked engines, before vs. after, treatment vs. control.
Sample~400 pages, matched pairs, recruited from the Index's panel of participating site owners.

Why 400 pages, specifically

A sample size decision should be justified, not arbitrary. 400 pages, 200 matched pairs, is set to give the study a reasonable chance of detecting a moderate effect size if one exists, based on typical citation-rate variability observed in preliminary Index data collection. It also remains a recruitable number, given a volunteer panel of participating site owners.

A smaller sample risks a false null result simply from insufficient statistical power. A much larger one would delay the study's first result well past what a reasonably-sized volunteer panel can practically support. This is a stated trade-off, not a guarantee against a false negative. A genuinely small true effect could still go undetected at this sample size, a limitation acknowledged directly in §11.

What would change our mind

A statistically significant, replicated increase in citation rate for the treatment group, holding all matched variables constant, across more than one collection window. Not a single-window fluctuation, which is exactly the kind of noise the Index's variance measurement is designed to catch.

Schedule

Recruitment begins alongside Index v1 collection in Q1 2027. First result reported no earlier than two full collection windows after enrollment closes.

What either outcome would mean for the field

A confirmed null result would be genuinely significant. It would mean one of the most universally repeated GEO recommendations in circulation has no demonstrated causal effect. That would free practitioners to redirect the time currently spent on schema toward tactics with stronger evidence, per the tactic scoreboard.

A confirmed positive result would be equally significant, in the opposite direction. It would suggest schema's effect operates through a mechanism, likely indexing or pre-retrieval processing, that the existing direct-fetch studies simply weren't positioned to detect. That would reopen a question the field had started to treat as settled against schema.

What to do with schema right now

You don't need this study's final result to decide today. Schema still has real, well-evidenced value for classic Google search: rich results, click-through rate. Keep it for that reason alone if you already have it.

Just don't treat it as a proven AI-citation lever yet. If you're choosing where to spend limited time, the current evidence favors tactics with a stronger track record, per the tactic scoreboard, over adding schema purely as a speculative AI-citation bet.

Limitations

  • A null result on this specific schema treatment doesn't rule out every possible schema use — it tests the most common types (Article/Product/FAQ) added to pages that previously had none.
  • Site owners who volunteer for a panel are not a random sample of the web — a known limitation of every volunteer-recruited study, stated plainly rather than hidden.
  • A sample of 400 pages may lack the statistical power to detect a genuinely small effect, as noted in §7 — a null result at this sample size describes "no detectable effect at this scale," not "provably zero effect."
How to cite this
Namdev, R. (2026). Does schema markup increase AI citations? (v1). Retrieved from https://ritiknamdev.com/blog/schema-markup-ai-citations-study

Published under CC BY 4.0 — reuse freely with attribution.

Related work on this site

Registered as Tier 3 research in the AI Citation Index roadmap. See the current evidence grade in the GEO tactic evidence scoreboard.

§ References

Sources

Figures attributed to third parties above have not been independently verified unless stated otherwise.

FAQ

Frequently asked questions

Hasn't this already been tested?
Partially. Ahrefs tracked 1,885 pages that added schema and found citations "barely moved." That's a real, disclosed observational test. But it wasn't randomized. Pages that add schema also tend to invest in other things: technical SEO, content quality, backlinks. Any of those could independently drive citation, so the observational design can't rule out those confounds.
What would a positive result actually prove?
That adding schema to a page causally increases its AI citation rate, holding other factors constant. That would be the first randomized evidence either way in this field.
Why does the study need a panel of pages rather than just your own site?
A single site's pages share one domain's authority, backlink profile, and content style. Any effect, or lack of one, could be specific to that site. A panel across multiple, unrelated site owners lets the effect, or null result, generalize.
Isn't it unusual to publish a study design before running it?
It's standard practice in science, and almost unheard of in SEO research. See the AI Citation Index for the full case for pre-registration. It's what prevents a null result from quietly disappearing.
Why does the debate over schema and AI citation generate so much disagreement compared to other tactics?
Likely because schema markup is cheap and easy to implement. That makes it an attractive recommendation for content and SEO tools to promote regardless of proof. It also has a genuinely intuitive-sounding mechanism, structured data should help a machine understand a page, that turns out not to be straightforwardly confirmed by the direct-fetch evidence available.
What happens to pages in the control group after the study ends?
Participating site owners are free to add schema to their control-group pages once the study concludes. The control period is temporary and specific to the measurement window, not a permanent restriction on those pages.
Ritik Namdev
Written by

Ritik Namdev

Growth · SEO · GEO

Growth marketer documenting a brand-new site's climb into Google and the AI engines - in public, with real numbers. Every tactic here is tested on real sites before it's published.

The Lab · Weekly

One experiment. Every week.

The field notes in your inbox - one thing I tested, the raw numbers behind it, and what it means for getting cited by AI.

Free forever. Unsubscribe anytime.