Schema markup is far more common on pages cited by AI. But a new Ahrefs report found that adding it didn’t result in a clear increase in citations.
Ahrefs tracked 1,885 web pages that added JSON-LD schema. Each page was matched against control pages that never added schema, and citation changes were measured across Google AI Overviews, AI Mode, and ChatGPT.
No platform showed a meaningful citation increase after schema was added.
What Ahrefs Found
The report analyzed 6 million URLs and found that pages cited by AI were roughly three times more likely to include JSON-LD. This gap has been seen as evidence that schema improves AI visibility. However, Ahrefs tested whether this held true when isolated from other signals, since sites with schema tend to invest in better content and earn more links.
They ran a controlled comparison, matching each schema page with three control pages from different domains with similar citation levels that never added JSON-LD. Citation changes were measured 30 days before and after schema addition.
Using its Brand Radar tool and Agent A, Ahrefs conducted a matched difference-in-differences analysis to account for platform trends. Here’s what was found.
- Google AI Overviews: −4.6% (a small but statistically notable decline relative to controls)
- Google AI Mode: +2.4% (too small to distinguish from random variation)
- ChatGPT: +2.2% (too small to distinguish from random variation)
Three more tests were run alongside the primary comparison, and all four found no clear positive or negative effect.
The AI Overview Decline
The −4.6% decline in the AI Overview section deserves context. Ahrefs reports both treated and control pages were already declining before schema was added. Treated pages declined slightly faster, but the difference is small, with about 12 fewer daily citations per page in a sample where most pages received hundreds.
The report notes that the decline could reflect a small negative effect from schema, or it could be coincidence. It doesn’t draw a conclusion either way.
What The Report Doesn’t Cover
Every page in the dataset had 100+ AI Overview citations before any schema was added. These pages were already in the consideration set, being crawled and surfaced.
The report admits this limitation. For pages not yet visible to AI, schema might still aid crawling, parsing, or indexing, but the data can’t confirm this.
The report also notes other limitations. Pages adding JSON-LD often change other elements, making it hard to separate schema effects from those changes. All schema types were pooled, so some might perform differently. The 30-day window might miss slower effects.
A searchVIU experiment cited in the report tested whether five AI systems used schema markup when fetching pages in real time. None did; they only extracted visible HTML, ignoring JSON-LD, Microdata, and RDFa. This was a direct-fetch test, not proof of schema’s role during training, indexing, or retrieval.
Why This Matters
Schema markup is frequently recommended for AI visibility. However, Ahrefs’ data complicates this. While schema supports rich results and knowledge graphs, adding JSON-LD doesn’t increase AI citations for pages already cited.
The data shows a correlation: pages with schema are cited more often by AI, but Ahrefs interprets this as a sign of overall site quality rather than schema’s direct impact.
Looking Ahead
The report can’t determine whether schema helps pages that aren’t yet cited, which is a different group of pages that need another study. If pages are visible to AI, JSON-LD probably won’t boost citations.
Featured Image: Roman Samborskyi/Shutterstock
