How is this check scored?
Every threshold on this page comes from one source: the citation-readiness scorer Gadex publishes. Per Gadex's own build, the weights below are read directly from that scorer and a test fails the build if the documented figure stops matching the applied one. A pass earns the full 5 points, a warning earns half, a fail earns none.
| Result | How it is decided |
|---|---|
| Pass | A heading matches method, methodology, how we (measured, checked, built, verified…), our process, data source, or sample size. |
| Warn | That wording appears in body text but not as a heading. |
| Fail | No methodology wording anywhere. |
Why does this check exist?
A claim is only as good as the account of how it was reached. For a page carrying original data, the methodology is what converts an assertion into evidence someone else can evaluate.
A heading scores higher than a passing mention because it makes the account findable. A model retrieving the claim can retrieve the method alongside it; a reader who doubts the number knows where to look.
The check accepts verification wording — "how we checked these figures" — as well as measurement wording. For pages whose original work is fact-checking rather than measuring, that is the natural phrasing, and it used to score zero.
How do you fix it?
- Give the method its own heading, not a parenthetical. If the page carries data, the reader is entitled to a section.
- Say what was measured, over what population, when, and what the known limitations are. A stated limitation increases credibility rather than reducing it.
- Where the page carries no original data, do not manufacture a methodology section. This check is worth five points and a fabricated section is worth less than nothing.
How often do pages fail this check?
Per Gadex's own measurement across the 91 content pages on this site, using the checker published at /tools/ai-search-visibility-checker/: 55 pass, 31 carry a warning, and 5 fail. Per that same run, 40 per cent of Gadex pages have something to fix on this check alone.
Those figures include the pages Gadex fails. A checker whose author exempts itself from the checking is marketing rather than measurement, so the numbers are generated from the built site on every deploy and the build fails if the published figures stop matching what Gadex actually scores. When Gadex fixes pages, the numbers move on their own.
What does this check miss?
- The check matches wording, not substance. A heading that says "Our methodology" above two vague sentences passes.
- It cannot tell whether the method described supports the claims made.
- Pages that legitimately have no methodology — a definition, an opinion piece — fail a check they cannot pass. That is a known cost of a fixed rubric; five points is deliberately small for this reason.
Where does this guidance come from?
The scoring rules are Gadex's. The reasoning about why these properties matter draws on the platforms' own published guidance:
- Google Search Central: creating helpful, reliable, people-first content — on self-evident expertise, sourcing, and who the content is for.
- Google Search Central: Article structured data — on author and date fields, and what they are used for.
- OpenAI: bots and crawlers — on how ChatGPT fetches and attributes pages it surfaces.
How we measured this
The counts above come from running the Gadex scorer over the built HTML of every content page on this site, reading each page's main content region only — nav, header and footer links are excluded, because a visitor pastes an article rather than a whole document. Legal boilerplate, the 404 page and generated tool result renderings are excluded as pages where the score would be meaningless. Per that run, the 91 pages counted are the ones a reader could plausibly ask an assistant to summarise.
The scoring thresholds on this page are read from the same module the tool runs, and a test fails the build if the weight documented here stops matching the weight the scorer applies. What none of this can tell you is whether an answer engine will cite a page: citation depends on the model, the prompt, the index and the competing sources, none of which is visible in your markup.
Common questions
Does a marketing page need a methodology section?
Only if it makes claims that rest on measurement. A pricing page does not. A page asserting that your approach produces better results does, and the absence of one is a fair thing for a reader to notice.
How much detail is enough?
Enough that a competent reader could challenge it. What you measured, over what, when, and what you could not measure. Precision about limits is the part most pages skip and the part that carries the most credibility.