How a number gets printed

Narrow screen: scroll the table sideways for more columns.

Two routes are published so far. The Claude Code CLI with web search is Anthropic’s own tool, not a scraper, and the Gemini answers come through Google’s own Gemini API. The earlier Gemini and Google AI Mode answers from the first research pass came from scripted browser sessions in signed-in accounts, which Google’s own systems rate-limited as unusual traffic after about 76 queries; that is not a route we publish numbers from, so those answers stay out. Production audits move Claude to the Messages API and add Google AI Mode through a disclosed data vendor.

Three answers to the same question can disagree. Asked “Best split keyboard for coding that will not take months to learn?” three times, Claude put Logitech first twice and Keychron first once. That is why every number on this site carries a range and a repeat count. Read the keyboards census, with both engines’ tables.

A keyword count says a name appeared, not how. In the pain relief census, store brands were mentioned 39 times. We read each mention in its sentence and coded it either as a product the answer told the reader to buy or as a qualifier: a place to buy, or one example in a list. 38 were qualifiers and 1 was a product. Two mentions could be read either way; the one closer to naming a product was counted as a product, against our own finding.

Before a domain an engine cites counts toward anything on this site, it gets three checks: its Tranco popularity rank, whether its homepage actually matches the category it is being cited for, and whether it shows signs of a recent ownership change (a domain that changed hands and now hosts something unrelated to its history). A domain that fails is marked flagged in words, never by colour. A domain that passes is marked verified. A domain we have not yet checked is marked unranked.

Narrow screen: scroll the table sideways for more columns.

Roughly one in seven of the Claude Code CLI’s citation instances in our research got flagged for a human look this way; on a human read, about a third of flags turned out to be on-topic after all. That precision figure stays internal and out of client-facing numbers until the flags are hand-labelled at scale, which is also why this page, not a client report, is where the caveat lives.

Every mention rate on this site carries a route, a repeat count and a date, which is the discipline this page exists to enforce. That discipline rules out the shortcuts that make a number easy to sell before it is earned: a ranking promised in advance, a point score with no repeat count behind it, or a consensus that was manufactured (bought reviews, hidden crawler text, incentivised posts) rather than measured. A number that cannot carry its route and its count does not get printed, on this page or anywhere else on the site.

robots.txt here allows the major search and AI crawlers: Googlebot, Bingbot, OAI-SearchBot, GPTBot, ClaudeBot, Claude-SearchBot, PerplexityBot and Google-Extended. Google-Extended specifically controls whether Google’s Gemini app can train on and ground its answers in this content. It does not control whether this site shows up in Google Search or in AI Overviews, which Googlebot governs on its own. We leave it allowed anyway: a census that cannot be read is not a census, and the trade-off is that anything crawlable here can also end up reused by a model we have no contract with.

• 2026-10-17: the route table now covers both published censuses, and the keyboards census grid replaces an illustrative grid as the worked example. Each census page keeps its own corrections log.
• 2026-10-16: first publication of the method page.