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 4 points, a warning earns half, a fail earns none.
| Result | How it is decided |
|---|---|
| Pass | The most repeated proper noun appears five or more times. |
| Warn | It appears three or four times. |
| Fail | No proper noun appears three times, or none is found at all. |
Why does this check exist?
A retrieval step has to decide what a page is about. A page that names its subject repeatedly makes that trivial; a page that introduces "the platform" once and then says "it" for 800 words makes it guesswork.
This cuts against a rule most writers are taught — vary your language, avoid repetition. For retrieval, consistent naming is the more useful property, and the tension is real rather than imagined.
The weight is low, at four points, because the signal is weak on its own. It matters most as a tiebreak between otherwise similar pages.
How do you fix it?
- Name the subject in each major section rather than relying on pronouns to carry across headings. A section retrieved alone should still say what it is about.
- Prefer the actual name to a category noun. "Gadex" beats "the service"; "WordPress" beats "the CMS".
- Do not stuff. Five mentions across a page is the bar, not five per paragraph, and a page that repeats a brand name mechanically reads like spam to both audiences.
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/: 80 pass, 10 carry a warning, and 1 fail. Per that same run, 12 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 counts capitalised tokens against a stop list, so it can pick the wrong subject — a frequently mentioned competitor, or a month name that slipped the list.
- It has no concept of synonymy. "Generative engine optimisation" and "GEO" count as different entities.
- A subject named in lowercase is invisible to it.
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 this reward keyword stuffing?
At the threshold, no — five mentions is what ordinary clear writing produces. The check has no upper bound, which is a genuine weakness, but a stuffed page will lose more on readability and on the paragraph checks than it gains here.
What if the page compares two things?
Then both should be named consistently, and the check will pick whichever appears more. That is fine: a comparison page where neither subject is named five times is probably leaning too hard on pronouns.