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 6 points, a warning earns half, a fail earns none.
| Result | How it is decided |
|---|---|
| Pass | Three or more figures with attribution nearby. |
| Warn | Fewer than three — including none at all. This check has no fail band. |
Why does this check exist?
A sourced specific is the most quotable thing a page can offer. It is precise enough to answer a question exactly and attributed well enough that a model can defend repeating it.
This check is the positive mirror of the unsourced-claims check. That one penalises figures without sources; this one rewards figures with them. A number counts for one or the other, never both, so the two cannot double-count the same sentence.
There is no fail band on purpose. Plenty of good pages — definitions, process explainers, opinion — have nothing worth quantifying, and failing them would invite padding with numbers nobody needed.
How do you fix it?
- Attach sources to the figures you already have. Most pages fail this check while having plenty of numbers, because none of them are attributed.
- Where you have first-party data, publish it with its methodology. Original measurement nobody else can copy is the strongest form of this signal.
- Do not add figures to satisfy the check. A page padded with irrelevant statistics scores better and reads worse.
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/: 14 pass, 77 carry a warning, and 0 fail. Per that same run, 85 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?
- Density is deliberately not measured. An earlier version required figures in 12 per cent of sentences, which punished thoroughness — every added sentence of explanation lowered the ratio — and made the score depend on subject matter rather than evidencing.
- The definition of a figure is the same heuristic used by the unsourced-claims check, with the same known gaps.
- Attribution is matched in a three-sentence window, so a source further away does not count.
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
Our page has no numbers. Are we penalised?
No. The worst outcome available is a warning, which costs three of the six points. That is the check saying there is an opportunity here, not that the page is defective.
Why is the bar an absolute three rather than a proportion?
Because a proportion makes the score depend on page length and on subject. Three sourced figures means the same thing on a 500-word page and a 3,000-word one: the page brings evidence.