Corrections & fact-checks

Peer-review pass. Tightened the epistemic boundary to the entry's own 'name the behavior, not the cause' rule: the definition now leads with the version mismatch; cache/retrieval layers are consistent-with, not asserted. Corrected the over-claim that true prevalence is likely higher (it is unmeasured; the observed count is only a lower bound on detectable events), and replaced 'expect weeks' with the actual 20-day observation and no published refresh SLA. Added two verified anchors: RESONEO's ChatGPT retrieval-stack study (reading cache serving copies 90+ days old) and OpenAI's offline-web-search docs.

Perplexity now cites this entry, surfacing it via the AI citation metrics hub page for the definition query; it joins the engines already citing it. The answer reproduced the coverage framing (your citations over all citations in the tracked prompt set) alongside a wall of competing definitions, so the term is broadly cited but the definitional space is crowded.

Microsoft Copilot now cites this entry (second-listed reference), reproducing the framing that passages must stay understandable when extracted independently and be self-contained, clear, sourced, and single-claim. Adds Copilot to the engines citing the term.

Clarified that a passing score proves single-fact retrieval, not merely that the model accepts long input, and not robust long-context understanding. Bounded RULER's 'half at 32K' finding to the 17 models it evaluated and flagged it as a 2024 snapshot whose exact fraction moves as models improve. Added the harder-benchmark progression with primary sources: NoLiMa (ICML 2025), which removes the lexical-overlap shortcut, and Sequential-NIAH (EMNLP 2025), which requires ordered needles. Framed the entry around vanilla NIAH within a larger test family, and added a context-rot cross-reference for the length axis.

Perplexity and Gemini now cite this entry for the definition query, reproducing the three-way distinction that citation, mention, and link are separate signals (grounding, naming, and a clickable URL). Two of five tested engines now cite it directly. ChatGPT and Claude cited third-party sources instead this time, so the term draws different sources on different engines.

Claude now cites this entry, reproducing the five-axis diagnostic framework (edge or location, cache state, path pattern, user agent plus referrer, and non-scraper user agent) and the confirmed-versus-candidate classification. Four of five tested engines now cite it directly; ChatGPT, Perplexity, and Gemini already did, each reproducing the same five axes. Microsoft Copilot did not cite it this time.

Perplexity now cites this entry, joining ChatGPT; two of five tested engines cite it directly. The answer reproduced the grounding-metadata framing (grounding chunks, grounding supports, and web search queries) and the distinction from Google AI Overviews and AI Mode. Claude, Copilot, and Gemini itself did not cite it this time.

ChatGPT now cites this entry directly for the definition query, listing it among its sources and reproducing its caveat that AI citation metrics are practitioner-created rather than standardized by peer-reviewed research; the answer closed by recommending per-engine, per-query tracking over a single blended visibility score. Two of five tested engines now cite it directly (ChatGPT and Perplexity).

ChatGPT and Perplexity both now cite this entry directly; with Claude, Copilot, and Gemini already citing it, all five tested engines have now cited this entry at least once. ChatGPT listed two of this glossary's pages as its top sources and reproduced the lock-down-the-denominator guidance; Perplexity cited the 40-of-100 worked example inline.

Microsoft Copilot now cites this entry (second in its references, after Brave's own documentation), reproducing the surfaces framing (AI Answers, Ask Brave, Featured Snippets, AI-powered descriptions) and the independent-index point that Brave citations reflect its own crawl and ranking decisions. Three of five tested engines now cite it directly.

Claude now cites this entry alongside the primary artifacts (the arXiv paper, GitHub, Hugging Face, OpenReview), including the comparison that the retrieval-ranking baseline outperformed the best C-SEO method by 7.6 times. Three of five tested engines now cite it directly, and ChatGPT cites it partially.

Microsoft Copilot now cites this entry first in its references, reproducing the six decisions a protocol locks down (query design, cadence, engine coverage, recording schema, disambiguation rules, signal thresholds) and the three failure modes of unstructured testing. With Copilot added, all five tested engines have now cited this entry at least once.

ChatGPT now cites this entry directly, where it previously appeared only in the folded sources list: the answer led with this page, and the rate-of-change versus snapshot framing plus the momentum-indicator caveat (velocity measures observed output, not the mechanism causing it) were cited inline. Four of five tested engines now cite it directly.

Microsoft Copilot now cites this entry first in its references, reproducing the three citation surfaces (WebSearch inline citations, DeepSearch reasoning traces, and structured citation fields in the xAI API) along with the native X integration and variable citation slot distinctives. Three of five tested engines now cite it directly.

Claude now cites this entry, opening its answer with a direct no and reproducing the Aggarwal et al. 2023 negative result (the only tested method to fall below baseline, at roughly 8 percent worse). Two of five tested engines now cite it directly.

Claude now cites this entry, reproducing the two-tier citation model: licensed publishers receive linked citations under the December 2025 content deals while other sources may appear unlinked, and social posts function as first-class sources alongside web pages. Two of five tested engines now cite it directly.

Microsoft Copilot now cites this entry first in its references, attributing the headline evidence row to it (position-adjusted word count 27.2 versus a 19.3 baseline, about a 41 percent relative gain, the largest measured lift among the nine methods tested). Four of five tested engines now cite it directly.

ChatGPT now cites this entry directly, where it previously appeared only in the folded sources list; it joins Perplexity and Microsoft Copilot, so three of five tested engines cite it directly. Both ChatGPT and Perplexity reproduced the retrieval, grounding, and attribution evaluation framing. Claude and Gemini did not cite it this time.

First confirmed AI-search citation for this entry: Microsoft Copilot lists it in its references for the definition query, alongside the 40 to 70 word extractable-answer framing. One of five tested engines now cites it; ChatGPT, Perplexity, Claude, and Gemini did not cite it this time.

Claude now cites this entry directly, reproducing the precision and recall asymmetry and the Liu, Zhang, and Liang (EMNLP 2023) benchmark (74.5 percent precision, 51.5 percent recall). With Claude added, all five tested engines have now cited this entry at least once across our probe rounds. This round Copilot placed it first in its references and ChatGPT cited it among its sources.

Perplexity now cites this entry directly (first in its sources), reproducing our framing that grounding reduces but does not eliminate hallucinations, since a grounded model can still misread a source or cite one that does not fully support the claim. It joins ChatGPT, so two of five tested engines cite it directly. Claude, Copilot, and Gemini did not cite it this time.

Microsoft Copilot now cites this entry, placing our page at the top of its sources and anchoring to the Aggarwal et al. 2023 result (PAWC 24.7 versus a 19.3 baseline, about 28 percent relative gain on citation visibility). Three of five tested engines now cite it directly, joining ChatGPT and Claude; Perplexity and Gemini did not cite it this time.

First confirmed AI-search citation for this entry: Perplexity cited it for the definition query, placing our page first and naming it as the key source, and reproduced the developer-facing provenance framing (inline reference links, search-grounded answers, attribution panels in the IDE). One of five tested engines now cites it directly; ChatGPT, Claude, Copilot, and Gemini did not.

ChatGPT now cites this entry: our reranking page appears in ChatGPT's source list for the definition query. One of five tested engines now cites it directly. As an established retrieval term, the citation sits alongside the canonical owners (Cloudflare, Inkeep) that lead the inline references rather than leading itself.

First confirmed AI-search citation for this entry: Microsoft Copilot cited it at the top of its sources for the definition query, reproducing the enforcement-versus-voluntary distinction (blocking as mandatory enforcement, unlike robots.txt or AIPREF signals). One of five tested engines now cites it directly; ChatGPT, Perplexity, Claude, and Gemini did not.

Perplexity now cites this entry for the definition query, joining ChatGPT; two of five tested engines cite it directly. Claude, Copilot, and Gemini did not cite it this time.

Gemini now cites this entry, joining Claude and Microsoft Copilot; three of five tested engines cite it directly. Gemini and Copilot both reproduced the per-engine attribution-rate figures (Perplexity around 29 percent; ChatGPT, Gemini, and Copilot around 7 to 8 percent; Google AI Overview 38 to 76 percent). ChatGPT and Perplexity did not cite it this time.

Microsoft Copilot now cites this entry, joining ChatGPT, Perplexity, and Gemini; four of five tested engines cite it directly. Multiple engines anchored to the Liu, Zhang, and Liang (EMNLP 2023) benchmark figures (74.5 percent precision, 51.5 percent recall). Claude cited a third-party source instead.

Broad citation gains for this entry: Perplexity, Claude, and Microsoft Copilot all now cite it directly, joining ChatGPT, and Gemini references it through the AI citation metrics overview. Four of five tested engines cite it directly and the fifth cites it partially. Copilot and ChatGPT used the term page itself, while Claude reached it through the citation-tracking page.

Perplexity and Gemini now cite this entry, joining Claude; three of five tested engines cite it directly and ChatGPT cites it partially. On Claude and Gemini the citation-velocity page itself was used, while ChatGPT and Perplexity reached it through sibling metric pages (AI citation metrics, citation share). Copilot did not cite it this time.

First confirmed AI-search citations for this entry: Perplexity and Gemini both cite it for the definition query, with Gemini using our definition as the opening line and rendering the select, order, and format pipeline. Two of five tested engines now cite it directly; ChatGPT, Claude, and Copilot did not.

Perplexity and Microsoft Copilot now cite this entry, joining Gemini; three of five tested engines cite it directly. Each placed our page at or near the top of its sources and used our practitioner-shorthand framing (the retrieval-corpus backend, split into passage chunks, embeddings, lexical data, and provenance). ChatGPT and Claude cited primary or academic sources instead.

Microsoft Copilot now cites this entry, placing it second in its sources and reproducing our negative-result framing from the Aggarwal et al. study (keyword stuffing performed 8 to 10 percent worse than baseline, the only method to fall below it). One of five tested engines cites it directly; ChatGPT, Perplexity, Claude, and Gemini did not.

Perplexity now cites this entry, joining Claude; two of five tested engines cite it directly. Both placed our page first and reproduced our practitioner-shorthand framing and the Statistics Addition method from the Aggarwal et al. study, including our caveat against chasing a raw density ratio. ChatGPT, Copilot, and Gemini did not cite it this time.

First AI engine citation: Perplexity surfaced this entry as a primary source for 'What is AI search evaluation?', citing the pillar above the fold alongside the opening definition. First engine to cite the entry since publication; 1 of 5 tested engines now cites it. Perplexity reached this explainer directly rather than the underlying academic sources.

First AI engine citations: ChatGPT, Perplexity, and Claude all surfaced this entry for 'What is AIPREF (AI usage preferences)?', each drawing on our preferences-versus-authentication distinction (AIPREF declares usage preferences; it does not authenticate the requester, which is the separate Web Bot Auth effort). From 0 to 3 of 5 tested engines citing the entry.

First AI engine citation: Perplexity cited this entry for 'What is authority signals?', drawing on our citations-and-backlinks breakdown alongside established SEO glossaries. 1 of 5 tested engines now cites it.

Second AI engine citation: Perplexity surfaced this entry as its top source for 'What is Black-hat C-SEO?', listing it first in the answer's source list and drawing on our prompt-injection-and-deception framing. Joins Gemini; 2 of 5 tested engines now cite it.

Copilot citation confirmed for 'What is Citation Footprint?', reproducing our coined framing (a cumulative, monotonic count of distinct cited URLs measuring coverage rather than intensity, distinct from citation share and citation velocity). Fourth engine to cite this coined entry; 4 of 5 tested engines now cite it.

First AI engine citations: ChatGPT and Perplexity both surfaced this entry for 'What is Citation hallucination?', with ChatGPT ranking it the top source and Perplexity drawing on our core distinction (a hallucinated citation points to a source that does not exist, separate from misquoting a real source or answering with none). 2 of 5 tested engines now cite it.

Gemini citation confirmed for 'What is cite-ability in AI search?', with our entry dominating the source panel and Gemini reproducing the four-trait framing (context-free quote, answer-first layout, factual density, echo-and-expand). Fourth engine to cite this practitioner-coined entry; 4 of 5 tested engines now cite it.

First AI engine citations: Perplexity and Gemini both surfaced this entry as their top source for 'What is Deep research mode?', each reproducing our framing that deep research mode is an escalation of agentic retrieval applying query fan-out at much larger scale. 2 of 5 tested engines now cite it.

ChatGPT citation confirmed for 'What is Freshness signals?', surfacing this entry as the top source and drawing on our metadata-signals breakdown (datePublished, dateModified, Last-Modified headers, version history). Joins Perplexity; 2 of 5 tested engines now cite it.

Perplexity citation confirmed for 'What is GEO content methods?', surfacing this pillar as its top source and reproducing our negative-result framing (most headline content tweaks were weak or null levers in Aggarwal 2023, and retrievability matters more than stylistic rewrites). Joins Gemini; 2 of 5 tested engines now cite it.

Perplexity citation confirmed for 'What is Position-Adjusted Word Count?', surfacing this entry as its top source, ranked above the original GEO paper it explains. Joins Claude; 2 of 5 tested engines now cite it.

First AI engine citation: Perplexity cited this entry as its second source for 'What is Retrievability?' (after Wikipedia), drawing on our Azzopardi and Vinay 2008 grounding and the framing that retrievability is an upstream lever on-page content tweaks cannot fix. 1 of 5 tested engines now cites it.

Same-day peer-review pass: corrected the Chatbot Arena attribution (Arena ranks models on crowdsourced human votes; the LLM judge scores MT-Bench, and the study used Arena's human data to validate the judge), scoped the over-80% human-agreement figure to the original study's settings, and added that the GEO benchmark's subjective-impression metric is itself G-Eval/GPT-scored, so verbosity bias may explain part of some content tactics' measured lift. Softened 'introduced' to 'named and validated' and 'cancel position bias' to 'detect and reduce'.

Perplexity citation confirmed for the definition query. Perplexity surfaced the AI citation metrics overview inline and in its sources-used list, reproducing the per-metric breakdown. First tracked engine to cite this pillar.

Perplexity citation confirmed for the definition query; the entry surfaced inline and in Perplexity's sources. First tracked engine to cite this entry.

Perplexity citation confirmed for the definition query, with the entry surfaced as a top source in Perplexity's answer. Joins ChatGPT among the engines citing this entry.

Perplexity citation confirmed for the definition query, with the entry surfaced as the top source. Joins ChatGPT among the engines that have cited this entry.

Now cited by ChatGPT, Perplexity, and Gemini for the definition query, the first citations for this coined metric. Perplexity and Gemini surfaced the citation footprint page directly; ChatGPT reached it through the terms index. Each answer carried the coinage framing and the cumulative, breadth-over-intensity distinction.

ChatGPT and Claude citations confirmed for the definition query, joining Perplexity and Gemini, so four of the five tracked engines now cite this entry. Each reproduced the probe-versus-protocol distinction and the fixed-panel methodology.

Gemini citation confirmed for the definition query. The metric surfaced in Gemini's answer through the related AI citation metrics and citation footprint pages, using the share-of-voice framing.

Microsoft Copilot citation confirmed for the definition query, with the entry ranked the top source in Copilot's panel. Third tracked engine to cite this entry, joining ChatGPT and Perplexity.

Perplexity citation confirmed for the definition query; the entry surfaced in the Sources list of Perplexity's answer. Joins ChatGPT among the engines citing this entry.

Perplexity citation confirmed for the definition query, the first citation for this entry on any tracked engine. The entry ranked the top source in Perplexity's panel, carrying its two-tier (licensed-publisher versus general-web) framing into the answer.

Perplexity citation confirmed for the definition query, with the entry surfaced as a source in Perplexity's panel. Joins ChatGPT among the engines citing this entry.

Perplexity citation confirmed for the definition query, the first citation for this entry on any tracked engine, with the page ranked the top source.

ChatGPT and Microsoft Copilot citations confirmed for the definition query, each surfacing this entry as the top source. They join Perplexity, so three tracked engines now cite it. The page carried its passage-level retrieval framing into both answers.

Peer-review pass: softened the framing so the cutoff reads as a primary driver of retrieval and the citation surface, not the sole cause (retrieval also serves verification, long-tail knowledge, and user-requested sources). Reframed retrieval triggering as multi-factor (query type, uncertainty, product policy, user request), not a before/after-cutoff line. Surfaced per-engine differences into the body (Perplexity nearly always retrieves, ChatGPT conditionally, Claude answers stable knowledge without searching). Added an OpenAI model-docs anchor.

Now cited by all five tracked engines, the first GEO Glossary entry to reach every engine we track. Perplexity and Microsoft Copilot are the two newest to cite this metric, joining ChatGPT, Claude, and Gemini. In each case it surfaced through the AI citation metrics overview that defines it, carrying its linked-versus-unlinked distinction into the answer.

Now cited by Claude for the first time, bringing the count to two of five tracked engines. Claude assembled its answer from a cluster of related GEO Glossary method entries (Quotation Addition, Fluency Optimization, Authoritative Statement Strength, Statistical Density, and Definition-Lead Style) rather than from a single page, citing Quotation Addition first. It shows how a method built on several techniques can surface through the entries that define each one.

Now cited by Claude, the second of five tracked engines to cite the entry after ChatGPT. Claude drew the definition and the practical rules directly from this page, reproducing the answer-block-opening framing and the inverted-pyramid analogy it uses to explain leading with the definition.

Now cited by ChatGPT, joining Claude as the second of five tracked engines to cite the entry. ChatGPT used this page as its lead source and reproduced its Position-Adjusted Word Count framing for the method.

Now cited by ChatGPT, the first of five tracked engines to cite the entry. ChatGPT surfaced this page among its sources when answering what hallucination grounding is, alongside other AI reference glossaries.

Revalued the supporting Aggarwal PAWC figure to the paper's position-adjusted 'Overall' column (quotation addition 27.2 versus a 19.3 baseline); the earlier figure (27.8 vs 19.5) was the paper's plain Word Count sub-column.

Corrected the Aggarwal Table 1 figures: the values previously cited as PAWC (Authoritative 21.8 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Authoritative 21.3 vs baseline 19.3, a raw +10%), which is the metric the paper's headline gains are computed on. The load-bearing finding is unchanged: the paper characterizes Authoritative tone verbatim as 'no significant improvement', a null result regardless of the raw percentage.

Corrected the Aggarwal Table 1 figures: the values previously cited as PAWC (Cite Sources 24.9 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Cite Sources 24.6 vs baseline 19.3, about +27%; Quotation Addition 27.2 about +41%; Keyword Stuffing 17.7 about -8%), which is the metric the paper's headline gains are computed on. The named top-3 framing and the 4th-place standalone ranking are unchanged.

Revalued the supporting Aggarwal PAWC figures in the footnote to the paper's position-adjusted 'Overall' column (Cite Sources 24.6, Quotation Addition 27.2, baseline 19.3); the earlier figures (24.9 / 27.8 / 19.5) were the paper's plain Word Count sub-column, not its position-adjusted metric.

Revalued the supporting Aggarwal PAWC range to the paper's position-adjusted 'Overall' column (~27% to ~41% lift); the earlier range (~28% to ~43%) was derived from the paper's plain Word Count sub-column.

Corrected the Aggarwal Table 1 figures: the values previously cited as PAWC (Fluency Optimization 25.1 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Fluency Optimization 24.7 vs baseline 19.3, about +28%; Quotation Addition 27.2 about +41%; Keyword Stuffing 17.7 about -8%), which is the metric the paper's headline gains are computed on. Rankings unchanged (Fluency still 3rd by standalone score, still not in the paper's named top-3).

Corrected the Aggarwal Table 1 figures throughout the methods table and footnote: the values previously cited as PAWC (Quotation Addition 27.8 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Quotation Addition 27.2 vs baseline 19.3 about +41%, Keyword Stuffing 17.7 about -8%), which is the metric the paper's headline gains are computed on. The verdicts, the named top-3, and the null/negative findings are unchanged.

Corrected the Aggarwal Table 1 figures: the values previously cited as PAWC (Keyword Stuffing 17.8 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Keyword Stuffing 17.7 vs baseline 19.3, mathematically about -8%), which is the metric the paper's headline gains are computed on. The negative-result finding is unchanged: Keyword Stuffing is still the only method scoring below baseline, and the paper's verbatim 'little to no performance improvement' framing stands.

Revalued the Aggarwal per-method figures in the footnote to the paper's actual position-adjusted PAWC values (the 'Overall' column: Quotation Addition 27.2 vs baseline 19.3, about +41%). The earlier figures (27.8 vs 19.5) were the paper's plain Word Count sub-column, not its position-adjusted metric.

Revalued the Aggarwal per-method figures in the footnote to the paper's actual position-adjusted PAWC values (the 'Overall' column: Quotation Addition 27.2 vs baseline 19.3, about +41%). The earlier figures (27.8 vs 19.5) were the paper's plain Word Count sub-column, not its position-adjusted metric.

Corrected the Aggarwal Table 1 figures: the values previously given as PAWC (baseline 19.5, Quotation Addition 27.8, and so on) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: baseline 19.3, Quotation Addition 27.2 at about +41%, Keyword Stuffing 17.7 at about -8%), which is the metric the paper's headline gains are computed on. Also fixed the metric symbol to Imp_pwc and clarified that PAWC is computed over the sentences that cite a source, so it measures attributed word share within an answer rather than citation frequency or rank.

Corrected the Aggarwal Table 1 figures: the values previously cited as PAWC (Quotation Addition 27.8 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Quotation Addition 27.2 vs baseline 19.3, about +41%; Keyword Stuffing 17.7, about -8%), which is the metric the paper's headline gains are computed on. The named top-3 framing and rankings are unchanged (Fluency Optimization is still 3rd by standalone score).

Corrected the Aggarwal Table 1 figures: the values previously cited as PAWC (Statistics Addition 25.9 vs baseline 19.5, and the rest) were the paper's plain Word Count sub-column. Updated to the paper's actual position-adjusted Word Count (the 'Overall' column: Statistics Addition 25.2 vs baseline 19.3, about +31%; Quotation Addition 27.2 about +41%; Keyword Stuffing 17.7 about -8%), which is the metric the paper's headline gains are computed on. Rankings and the named top-3 framing are unchanged (Statistics Addition still 2nd by standalone score).

Revalued the supporting Aggarwal PAWC figures to the paper's position-adjusted 'Overall' column (Statistics Addition 25.2 vs baseline 19.3, Quotation Addition 27.2, Cite Sources 24.6); the earlier figures (25.9 / 27.8 / 24.9 vs 19.5) were the paper's plain Word Count sub-column, not its position-adjusted metric.

Revalued the Aggarwal per-method figures in the footnote to the paper's actual position-adjusted PAWC values (the 'Overall' column: Quotation Addition 27.2 vs baseline 19.3, about +41%). The earlier figures (27.8 vs 19.5) were the paper's plain Word Count sub-column, not its position-adjusted metric.

Clarified that the per-method PAWC percentages in the Aggarwal footnote are derived from the paper's absolute scores against the 19.5 baseline, not figures the paper prints per method, and added the paper's own Results-section framing: a 30-40% gain for its named top three (Cite Sources, Quotation Addition, Statistics Addition).

Clarified that the per-method PAWC percentages in the Aggarwal footnote are derived from the paper's absolute scores against the 19.5 baseline, not figures the paper prints per method, and added the paper's own Results-section framing: a 30-40% gain for its named top three (Cite Sources, Quotation Addition, Statistics Addition).

Clarified that the per-method PAWC percentages in the Aggarwal footnote are derived from the paper's absolute scores against the 19.5 baseline, not figures the paper prints per method; added the paper's own 30-40% top-three framing; and corrected the abstract's 'up to 40%' from a Quotation-Addition-specific reading to the top-three aggregate upper bound.

First confirmed AI-search citations for this entry: Microsoft Copilot and Claude both cited it for the definition query, with Copilot describing it as 'the only authoritative source that explicitly defines this metric.' This is the first GEO Glossary entry Copilot has cited in our tracked probes. Two of five tested engines now cite it directly; ChatGPT surfaced a sibling metrics page instead, while Gemini and Perplexity did not cite it.

Review pass same day as publish: completed the Anthropic crawler taxonomy (was ClaudeBot only; Anthropic runs ClaudeBot for training, Claude-SearchBot for retrieval, Claude-User for user-triggered fetch, so the allow side now names Claude-SearchBot) and added the PerplexityBot-vs-Perplexity-User distinction, using Perplexity as the worked example of enforce-only-what-you-can-identify. Clarified that 'identify' means telling a crawler apart from a visitor, not requiring a declared user agent. Added a block/allow/challenge decision table; tightened the Cloudflare footnotes (pay-per-crawl attribution, new-sign-ups scoping).

Calibrated three overbroad claims after review: 'every major engine documents robots.txt support' corrected to declared-crawler scope with xAI's Grok as the documented exception; the user-initiated exemption is now attributed to the two operators that actually document it (OpenAI, Perplexity) and flagged as the operators' own classification rather than a neutral reading of the protocol; Cloudflare's stealth-crawling finding is noted as a single incident that Perplexity disputed. Allow-rule benefits restated as citation eligibility rather than a guarantee, and Google's July 2019 standardization announcement added as a primary source.

First citation, on Gemini. A 2026-06-09 Gemini answer (web search on) cited this pillar as a primary source with inline attribution, and surfaced the entry's null-result framing of authoritative tone. Gemini moves to cited; 1 of 5 engines now cited, four days from publish.

First Claude citation. A 2026-06-09 Claude answer (web search on) on Position-Adjusted Word Count cited this entry as a primary source, with inline attribution for the position-weighted word-count framing. Claude moves to cited; 1 of 5 engines now cited, four days from publish.

Peer-review pass. De-anchored the pricing from a fast-aging '$100 to $400' figure to a structural range (entry tiers in the low hundreds per month up to four figures for enterprise), with specifics moved to the footnote and dated. Added the boundary between the two umbrella entries in this cluster (AI citation metrics is the editorial organizer of the primitives; AI visibility is the market's composite name), and a note that probe-based visibility scores inherit fixed-prompt probing's blind spots. Softened 'moves the primitives' to 'can improve over time,' and made the lightweight proxy per-engine and per-prompt-set.

Removed an unsourced figure from the shared Aggarwal footnote: a previously-asserted 'Average 31.4% in combinations' for Cite Sources was found unlocatable in the GEO paper on re-check (ar5iv full text + web search). The verbatim facts are unchanged: the paper names Cite Sources in its top-3 despite its 4th-place standalone score without stating why, and the only combination result it reports is Fluency plus Statistics outperforming any single method by more than 5.5%.

First confirmed ChatGPT citation: ChatGPT surfaced this entry as a GEO Glossary source for the 'what is Brave Search AI citation' definition query. The chatgpt status moves from untested to cited.

First confirmed ChatGPT citation: ChatGPT surfaced this entry among its sources (in the folded 'more sources' tray) for the 'what is ChatGPT search citation' definition query. The chatgpt status moves from untested to cited.

First confirmed Perplexity and Gemini citations: both surfaced this entry as a top source for the 'what is citation probe protocol' query, with Perplexity ranking it first and Gemini's source panel listing several GEO Glossary entries for it. The perplexity status moves from not-cited to cited and gemini from untested to cited.

Removed an unsourced figure surfaced while building the GEO content methods pillar: a previously-asserted 'Average 31.4% in combinations' for Cite Sources (offered as the reason it appears in the paper's named top-3 over Fluency) was found unlocatable in the GEO paper on re-check via the ar5iv full text and a web search. The verbatim facts stand: the paper names Cite Sources in its top-3 despite its 4th-place standalone score, without stating why; the only combination result it reports is Fluency plus Statistics outperforming any single method by more than 5.5%.

Completed the engine roster after peer review: added Microsoft's Researcher in Microsoft 365 Copilot (March 2025, distinct from the Think Deeper toggle) and Anthropic's Claude Research (April 2025), so all five tracked engines are covered, and re-scoped the December 2024 to February 2025 window as the first wave with Microsoft and Anthropic following that spring. Softened over-general claims (broadly similar rather than near-identical; products differ; Gemini Deep Research is not stated to use query fan-out, only Google's Deep Search is). Added a note that deep research is the most expensive, least-probed citation surface.

Added the first causal-isolation evidence on how much AEO actually moves traffic: a 2026 single-domain natural experiment (Glasp.co) found ChatGPT referrals grew 5.7x overall but only about 1.82x after removing platform-level growth (untreated pages on the same domain grew 3.5x on tailwind alone), so headline AEO multiples overstate the causal effect. Framed as a single-site result, not a generalizable estimate.

Added the grounded-AI-search side: a Tow Center study of eight grounded tools found wrong citations in over 60% of responses, with over half of Gemini and Grok 3 responses citing fabricated or broken URLs. Introduced the hybrid failure mode it surfaces (the source is real but the link is fabricated, broken, or points to a syndicated copy), distinct from a wholly non-existent source. Softened claims that grounded retrieval reduces the problem (it does not remove broken-link or misattribution failures), broadened the definition to cover fake cases and quotations, and corrected the Mata sanction to the two lawyers and their firm.

Corrected an attribution error: the 'cited from beyond the top 10' pattern is measured for the standalone assistants (ChatGPT, Gemini, Copilot, Perplexity), not for Google's AI Overview, whose citations come disproportionately from the top 10 (about 38% in Ahrefs' 2026 update, down from 76% in 2025). Turned that contrast into a finding (AI Overview hugs organic ranking while independent assistants nearly decouple), softened the AI Overview claim to a 'correlate', noted that Ahrefs' own opening sentence mis-attributes its 12% headline, and added the 15,000-prompt dataset size.

Claude citation confirmed for the definition query ('What is cite-ability in AI search?'). The entry surfaced as a cited source in Claude's web-search answer, alongside several third-party glossaries. Third engine to cite this entry (after ChatGPT and Perplexity); 3 of 5 tested engines now cite it. Notable because cite-ability is a practitioner-coined term with no upstream primary paper, so Claude cites this explanation directly rather than reaching past it to a canonical source.

Added a side-by-side disambiguation of LLMO against GEO, AEO, and AIO (the AI-search acronyms readers most confuse), plus two FAQ entries on whether LLMO and GEO differ in practice; the umbrella framing is hedged as contested to match the GEO and AIO entries. Also fixed two sourcing errors: the data-selection citation pointed to arXiv:2402.16827 (a pretraining-scoped survey) while the text described instruction tuning, now repointed to arXiv:2402.05123; and the LangChain default chunk size was off ~4x (RecursiveCharacterTextSplitter defaults to 4000 characters, not ~250 tokens).

Peer-review pass. Fixed the attachment draft's title ('Associating AI Usage Preferences with Content in HTTP', not 'Attaching...') and reframed the maturity reasoning: both drafts are adopted, still-active working-group documents, and the attachment draft's lapsed latest revision is the routine six-month Internet-Draft auto-expiry, not abandonment (it carries an Aug 2026 milestone). The watch-don't-deploy conclusion stands; the reasoning is now pre-standardization, not 'expired.' Also softened framing (effort-to-standardize vs finished standard; complementary to rather than successor to robots.txt).

Peer-review pass. Corrected the Status framing that treated contextual chunking (Anthropic) as the single 2024-2026 response to context loss; it is now presented as one of several approaches, alongside late chunking (Jina AI: embed the whole document, then split) and semantic chunking, with the late-chunking paper added as a non-vendor-single primary source. Tightened over-absolute claims (chunk as the retrieved unit, every production RAG system) to reflect that not all retrieval works by text chunking. Added a boundary note distinguishing chunking (splitting that produces units) from sub-document retrieval (selecting among the units).

Verified the venue against the ACL Anthology record (Transactions of the ACL, Vol. 12, 2024, pp. 157-173) and disambiguated the source from the other Liu et al. 2023 paper in the glossary, 'Evaluating Verifiability in Generative Search Engines' (arXiv:2304.09848), which shares the same first and senior author but is a different work; both are now cited by short title rather than a bare author-year. Also tightened the framing of front-loading as one evidence-backed mechanism among several, and clarified that BM25 and dense-similarity scoring do not weight within-body position even where production systems layer on field or heading boosts.

Perplexity and Gemini citations confirmed for the definition query ('What are citation precision and citation recall in AI search engines?'), both surfacing 'Citation precision and recall - GEO Glossary' as a primary source. Combined with the same-day ChatGPT citation, this entry is now cited by three engines (ChatGPT + Perplexity + Gemini).

ChatGPT citation confirmed for the definition query ('What are citation precision and citation recall in AI search engines?'). The entry surfaced as a 'GEO Glossary' source in ChatGPT search, alongside the Liu et al. verifiability paper and other references. First confirmed citation for this entry on any engine.

ChatGPT citation confirmed for the definition query ('What is an inverted index in information retrieval?'). The entry surfaced as a 'GEO Glossary' source in ChatGPT search, alongside Wikipedia and GeeksforGeeks. First confirmed citation for this entry on any engine.

Perplexity citation confirmed for the definition query ('What is passage-level optimization for AI search?'). 'Passage-level optimization - GEO Glossary' surfaced as a primary source. First confirmed citation for this entry on any engine.

Perplexity citation confirmed for the definition query ('What is sub-document retrieval in RAG?'). 'Sub-document retrieval - GEO Glossary' surfaced as a primary source alongside RAG-technique sources. First confirmed citation for this entry on any engine.

ChatGPT citation confirmed for the definition query ('What is authoritative statement strength in AI search content optimization?'), surfacing as a 'GEO Glossary' source. This completes four-engine coverage: ChatGPT, Perplexity, Claude, and Gemini all cite this entry, the first term on the site confirmed cited by four distinct engines.

Gemini citation confirmed for the definition query ('What is authoritative statement strength in AI search content optimization?'). Gemini surfaced the entry as a 'GEO Glossary' source and reproduced its framing (the paper-verbatim null quote plus the +11.8% raw-vs-statistically-null distinction). Third engine to cite this entry (Perplexity + Claude + Gemini), making it the glossary's most broadly-cited term.

Same-day revisions. Method names switched to the paper's own terminology (Simple Language / Citations / Quotes / Statistics rather than Aggarwal's Easy-to-Understand / Cite Sources / Quotation Addition / Statistics Addition); Aggarwal labels kept in parentheses. Added a second Discussion quote where the paper notes Aggarwal's own PAWC data, on inspection, also points to decreasing scores. Added specific evaluation LLMs (gpt-4o-mini + claude-3-5-haiku) as concrete anchor for the more-production-realistic framing. Clarified the paper benchmarks nine C-SEO methods plus a separate baseline (ten items total).

Gemini citation confirmed for the definition query ('What is citation match rate in AI search?'). The entry surfaced as a 'GEO Glossary' source in Gemini's answer, cited inline in several places. Third engine to cite this entry (after ChatGPT and Claude). Notable: citation match rate is a practitioner-coined metric with no vendor-canonical primary paper, so Gemini cites this explanation rather than an upstream source.

Claude citation confirmed for two of this entry's tracked queries: the definition query ('What is authoritative statement strength in AI search content optimization?') and the Aggarwal vendor-research query ('How did Aggarwal 2023 rank Authoritative tone among content methods?'). The entry surfaced as a primary source in Claude's desktop web-search answers. Same-day cross-engine signal: Perplexity also confirmed cited today across the same probes plus the operational variant.

Perplexity citation confirmed for all three of this entry's tracked queries: the definition query ('What is authoritative statement strength in AI search content optimization?'), the operational query ('Does using authoritative tone increase ChatGPT citation rate?'), and the vendor-research query ('How did Aggarwal 2023 rank Authoritative tone among content methods?'). The entry surfaced as a primary source with inline citations in all three Perplexity answers. First multi-probe citation event for this entry, one day after the lede was rewritten to lead with the paper's verbatim 'no significant improvement' framing.

Claude citation confirmed for the definition query ('What is citation match rate in AI search?'). The entry surfaced as a primary cited source in Claude's desktop answer. Cross-engine consistency: ChatGPT first cited this entry 2026-05-17; Claude now also cites for the same probe.

Claude citation confirmed for the definition query ('What is citation share in AI search?'). The entry surfaced as a primary cited source in Claude's desktop answer. First confirmed Claude citation for this entry.

Perplexity citation confirmed for the Aggarwal vendor-research probe ('What did Aggarwal 2023's GEO paper say about Cite Sources as a content method?'). Cite Sources Optimization | GEO Glossary surfaced as one of 11 sources, with the sibling Quotation Addition entry also cited inline. Citation comes one day after the entry's lede was rewritten to lead with the paper's verbatim named top-3 framing.

Perplexity citation reconfirmed for the definition query ('What is cite-ability in AI search?'). Cite-ability | GEO Glossary continues to surface as a primary source ten days after first observed citation on 2026-05-20, with inline citations across the answer body.

Claude citation confirmed for the Aggarwal vendor-research query ('What did Aggarwal 2023's GEO paper say about Fluency Optimization as a content method?'). The entry surfaced as a primary cited source in Claude's desktop answer. First confirmed Claude citation for this entry.

PAWC labeling sweep. Critical reframing: lede previously called Fluency Optimization 'one of the four top-performing single methods', but the paper's verbatim named top-3 (Cite Sources, Quotation, Statistics) does NOT include Fluency despite its 3rd-place standalone Table 1 PAWC. The paper's strongest framing of Fluency is the §5.3 Fluency-plus-Statistics combination pair (+5.5% over any single method), not as a named top single-method intervention. Aggarwal footnote labels values as 'Table 1 main GEO-bench' + Table 5 Perplexity.ai per-engine caveat.

Corrected the Mintlify blog post URL and announcement date. The Sources block referenced 'mintlify.com/blog/llmstxt' (404) with the date November 14, 2024; the actual post is 'Simplifying docs for AI with /llms.txt' at 'www.mintlify.com/blog/simplifying-docs-with-llms-txt', published November 20, 2024. Body sentence about the Mintlify platform-wide rollout date updated to match. Caught by the new site-wide link-audit pass across all 226 frontmatter source URLs.

Claude citation confirmed for the Aggarwal vendor-research query ('What did Aggarwal 2023's GEO paper say about Quotation Addition as a content method?'). The entry surfaced as a primary cited source in Claude's desktop answer. First confirmed Claude citation for this entry.

Claude citation confirmed for the Aggarwal vendor-research query ('What did Aggarwal 2023's GEO paper say about Statistics Addition as a content method?'). The entry surfaced as a primary cited source in Claude's desktop answer; it also surfaced as the cited source for the parallel Cite Sources Aggarwal query, a cross-entry signal.

Mechanism + adoption fact-check (same-day after publish). §How it works now lists three required headers (Signature-Agent, Signature-Input, Signature); Signature-Agent (not Signature-Input) carries the bot's key directory URL that the verifier reads to fetch the public key. Status in 2026 updated to the agent-first / crawler-later split: Google's experimental Google-Agent signs at agent.bot.goog and OpenAI's ChatGPT agent signs at chatgpt.com, while Googlebot, GPTBot, and OAI-SearchBot remain unsigned. Added IETF draft-meunier-web-bot-auth-architecture (Cloudflare + Google co-authored) and AWS Bedrock AgentCore implementer footnotes.

Critical paper-misrepresentation fix. Entry previously framed the Authoritative result as a '+11.8% measurable modest lift'. But Aggarwal Section 4 verbatim: 'one would expect a more persuasive and authoritative tone can boost visibility. However, to the contrary we find no significant improvement.' The +11.8% PAWC is a raw number; the paper itself frames it as null and reports no p-values. Description, metaDescription, lede, Status, C-SEO Bench section, and FAQs rewritten to lead with the paper-verbatim null. Raw PAWC retained for transparency. Entry was misrepresenting peer-reviewed research; correction restores cluster discipline.

Same-day peer-review revision. Critical lede fix: asymmetry was reversed (precision 74.5% > recall 51.5% means engines were better at faithful citation than at citing every claim-bearing sentence). Critical fact fix: removed unverified Profound per-response density numbers; replaced with the study's actually-reported source-concentration patterns. Added Li & Sinnamon 2024 + Profound footnotes to Sources. Softened the precision-failure framing, precision-recall trade-off, and hallucination-grounding definition. NeevaAI dates made precise. 2x2 labels improved. Back-links added to attribution-rate, cite-ability, pillar.