What SEOs believe, and what 12,778 AI answers actually did
A September 2026 survey asked 100+ SEO experts to rank Google's ranking factors. It produced 13,665 data points and never mentions AI search, AEO, GEO, LLM citation or Schema / structured data. We had been measuring the AI answer surface for 164 days. Here is where belief and measurement disagree.
The survey is not wrong for being a survey. It measures what practitioners believe an engine does, which is a real and useful thing to know. It is being read for something else: what engines actually do. Those are different kinds of claim, and only one of them can be checked against data.
Three collisions
Expert consensus
29.4%named behavioral click signals a top-tier ranking factor. User satisfaction polled under 20 percent.
What we measured
0.061%of the time, ChatGPT returns the identical set of sources twice.
Measured across 24,633 answer pairs. A surface that unstable does not hold still long enough for click signal to accumulate against a ranking.
Collision 1The factor assumes a stable ranking. On this surface we did not find one.
Expert consensus
AbsentSchema and structured data appear nowhere in the survey's ranked factors.
Matched-control experiment
−4.6%change in AI Overview citations after adding JSON-LD.
Ahrefs, 1,885 pages against 4,000 matched controls. Schema earns its place through entity resolution and rich results, not citation lift.
Collision 2Consensus and experiment agree. This is the one row where they do.
Expert consensus
0 mentionsAI search, AEO, GEO and LLM citation appear nowhere across all 13,665 data points.
What we measured
12,778answers across five engines over 164 days.
Across that window the surface the survey does not mention cited 8,577 distinct domains in 109,674 citation events.
Collision 3The largest gap is the one nobody was asked about.
Which engine you ask outweighs most factors on the list
Every answer in our corpus was a real query put to a real engine, repeated over months. The question we can answer that a survey cannot is whether an engine returns the same sources twice.
No ranking-factors survey has a row for which engine the question was asked in. On this evidence it moves the answer more than most rows that do exist.
The finding with money attached
If an engine rarely repeats itself, a single measurement of it is not a measurement. That is quantifiable, and it sets a floor on how many times a prompt must run before a change in AI visibility means anything.
| Runs | 95% CI | Verdict |
|---|---|---|
| 1 | n/a | no variance estimate at all |
| 2 | ±0.2067 | too noisy to act on |
| 3 | ±0.1688 | too noisy to act on |
| 4 | ±0.1462 | directional only |
| 6 | ±0.1193 | directional only |
| 8 | ±0.1033 | directional only |
| 9 | ±0.0974 | usable for large moves |
| 12 | ±0.0844 | usable for large moves |
| 14 | ±0.0781 | usable for large moves |
Below 9 runs per prompt, the confidence interval is wider than ±0.10. A tool reporting that your AI visibility improved this month, on fewer runs than that, is reporting noise. Most tools in this category run a prompt once.
Where the numbers came from
Measured, our corpus, recomputed 2026-09-17
- 12,778 answers · 5 engines · 164 days · 2026-01-13 to 2026-06-25
- Citation-set stability over 116,225 answer pairs, with 95% CIs from a cluster bootstrap
- Gini 0.8257 over 8,577 domains and 109,674 citation events; top 100 = 44.17%
- Measurement floor: pooled SD 0.1491 from 878 groups
Relayed, third party, linked at source
- Ranking factors expert survey, Cyrus Shepard and Dawn Shepard (Zyppy, September 2026). 100+ SEO experts, 13,665 data points. An opinion poll. Every percentage is a share of respondents who named that factor, not a weight inside Google. No sampling or elicitation methodology was published.
- Ahrefs schema matched-control study, 1,885 pages against 4,000 controls. The study population was pages already heavily cited. It shows schema will not push an already-cited page higher; it does not test whether schema helps a page with no citations get discovered.
Withdrawn, published by us, does not reproduce
- “Named is 2.7x more stable than cited” was published as 2.7x. It does not reproduce: 1.43x prevalence, 0.99x stability. A metric-definition error, not a coverage one. The published framing conflated prevalence with stability, and the two published numbers do not come from one consistent denominator. More data did not fix it.
Seven domains entered tracking on different dates. boatlaw.com (69 mentions over 7 days) sits below the reporting floor and is excluded from pooled conclusions. Controlled to the six domains present throughout, median Jaccard is flat across April and May.
The full dataset ships as JSON under CC BY 4.0. Re-use it, check it, or disagree with it in public.