--- title: "GEO myths: what primary sources say and what remains unanswered" description: "Four GEO myths and two claims with mixed evidence, checked against primary sources: what Common Crawl and Google document and what vendor studies show." url: "https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/" markdown_url: "https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias.md" lang: "en" date_published: "2026-11-12" author: "Martín Garay" author_url: "https://cookingmetrics.com/about-martin-garay/" publisher: "CookingMetrics" publisher_url: "https://cookingmetrics.com/" keywords: ["SEO for AI (GEO)"] citation_apa7: "Garay, M. (2026, November 12). *GEO myths: what primary sources say and what remains unanswered*. CookingMetrics. https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/" references_apa7: - "Common Crawl. (n.d.). *Frequently Asked Questions*. https://commoncrawl.org/faq" - "Malte Ostendorff, arXiv. (n.d.). *Host-Aware Web Crawling for LLM Pretraining Data (arXiv:2610.13321)*. https://arxiv.org/abs/2610.13321" - "Google Search Central. (n.d.). *AI features and your website*. https://developers.google.com/search/docs/appearance/ai-features" - "Google Search Central. (n.d.). *Optimizing websites for AI features in Google Search*. https://developers.google.com/search/docs/fundamentals/ai-optimization-guide" --- # GEO myths: what primary sources say and what remains unanswered > Four GEO myths and two claims with mixed evidence, checked against primary sources: what Common Crawl and Google document and what vendor studies show. - **Author:** [Martín Garay](https://cookingmetrics.com/about-martin-garay/) · Founder of CookingMetrics - **Published:** November 12, 2026 - **Topics:** SEO for AI (GEO) - **Web version:** https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/ ## How to cite this article (APA, 7th edition) Garay, M. (2026, November 12). *GEO myths: what primary sources say and what remains unanswered*. CookingMetrics. https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/ In-text citation: (Garay, 2026) ## References - Common Crawl. (n.d.). *Frequently Asked Questions*. https://commoncrawl.org/faq In-text citation: (Common Crawl, n.d.) - Malte Ostendorff, arXiv. (n.d.). *Host-Aware Web Crawling for LLM Pretraining Data (arXiv:2610.13321)*. https://arxiv.org/abs/2610.13321 In-text citation: (Malte Ostendorff, arXiv, n.d.) - Google Search Central. (n.d.). *AI features and your website*. https://developers.google.com/search/docs/appearance/ai-features In-text citation: (Google Search Central, n.d.) - Google Search Central. (n.d.). *Optimizing websites for AI features in Google Search*. https://developers.google.com/search/docs/fundamentals/ai-optimization-guide In-text citation: (Google Search Central, n.d.) --- **Several common GEO recommendations have no backing in primary sources.** The Common Crawl documentation consulted does not mention Internet Archive as a discovery route; Google states that no special files or markup are needed for its AI features; and vendor studies do not show that llms.txt, the top 10 or text length explain citations on their own. This guide is written for those who must decide where to invest time, not only for those who implement. Technical terms are explained in plain words and the detail goes under the label "For the technical team". [CookingMetrics](https://cookingmetrics.com/) offers audits and support to development teams, and does not sell visibility tools. Two of the cited sources come from companies that do sell SEO software; this is declared in each case. This guide is not a complete list of myths: it includes only those we could check against a primary source. ## In summary - A claim is called a "myth" here only if a primary source contradicts it or if there is no evidence in its favor. If the evidence is mixed, it is presented as uncertainty. - **Myth 1:** saving pages in Internet Archive is not listed in the Common Crawl documentation as a way for it to crawl them. There is no official backing; that does not prove it is impossible. - **Myth 2:** the fact that Common Crawl knows an address does not imply that it downloads it. Its own documentation says it archives a sample of the web. - **Myth 3:** Google states that there is no need to create new files, AI text files or special markup to appear in AI Overviews or AI Mode. This applies to Google's features, not to other assistants. - **Myth 4:** a vendor study of about 300,000 domains found no correlation between having llms.txt and being cited. There is no evidence in favor, and no definitive proof against either. - **Mixed evidence:** that being in the top 10 "ensures" citations and that long text is cited more are neither proven myths nor truths: the available studies come from vendors, with methods that change between versions. - Distinguishing between model **training** and real-time page **retrieval** avoids most of the confusion. ## How each claim was classified Each claim carries an evidence class, so it is clear how much weight what is said carries: - **Official documentation:** the service's own page on how it works. - **Study with a published method:** an analysis that explains its sample and its method. If it is published by a company that sells related products, this is stated. - **No source consulted:** the claim circulates, but we did not find a primary source that supports it. No class proves causality on its own. A correlation between two things, for example having a file and being cited, does not show that one causes the other. [Section for signed-in readers, level C: https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/#bloque-1] ## Before starting: training is not retrieval Much of the confusion comes from mixing two different processes: - **Training:** models learn from large collections of pages, which are filtered and processed beforehand. Common Crawl is one of the public collections of that kind. - **Retrieval:** when an assistant with search answers, it consults pages at that moment and may cite them. It is a different mechanism, with different robots and different rules; see [how to measure traffic from AI assistants](https://cookingmetrics.com/blog/como-medir-trafico-asistentes-ia/). Being in a training collection does not on its own explain a citation in an assistant with search, and the sources consulted do not say otherwise. ## Myth 1: "saving pages in Internet Archive makes Common Crawl pick them up" - **What the documentation says:** the [Common Crawl FAQ](https://commoncrawl.org/faq), consulted on November 12, 2026, states that its crawler uses the sitemaps announced in the `robots.txt` file and that it can find pages by following links from other sites. It does not mention Internet Archive. - **What it does not say:** it does not say that this list is exhaustive or that the practice is impossible. That is why this guide does not claim that the practice does not work: it claims that there is no official documentation that backs it. - **Evidence class:** official documentation, by absence. No source consulted for the claim. - **What is advisable instead:** declare the sitemap in `robots.txt` and keep links from other sites pointing to the important pages. They are the two routes the documentation mentions. ## Myth 2: "if Common Crawl knows an address, it downloads it" - **What the documentation says:** the same FAQ states that it does not usually archive a whole site, but a randomly chosen subset, and that the dataset is a sample of the web. - **What the study says:** a research paper, [Host-Aware Web Crawling for LLM Pretraining Data](https://arxiv.org/abs/2610.13321) (Malte Ostendorff, October 9, 2026), whose author is listed as affiliated with Common Crawl Foundation, analyzes how crawling is distributed across sites. With data from a 2024 crawl: - the correlation between how much of a site is crawled and its "quality density" is −0.08 across 5,654,186 sites; that is, there is almost no relationship; - the authors estimate, for that crawl, about 58 million high-quality pages among the known addresses that were left undownloaded. It is an estimate that assumes the undownloaded pages resemble the downloaded ones; - an alternative policy would achieve, in simulation, up to 7.8 times more high-quality pages per downloaded page with small budgets, and 1.7 times as the budget grows. - **What "quality" means here:** the prediction of a classifier on its usefulness for training a model. The paper itself treats it as an approximation, not as quality in an editorial sense. - **What it does not say:** that Common Crawl has changed its crawler, or that it will. The proposal was tested in simulation. It does not explain citations in assistants with search. - **Evidence class:** official documentation and study with a published method. The limitations section of the paper was not read; nothing is claimed about it. **For the technical team.** The correlation cited is Spearman's, a measure of how similar the order of two lists is, between −1 and 1; a value close to 0 indicates little relationship. The study uses a sample of WARC files (the format in which Common Crawl stores pages) and an index of sites for the full analysis. ## Myth 3: "you have to create a file or special markup to appear in Google's AI features" - **What the documentation says:** the Search Central page ["AI features and your website"](https://developers.google.com/search/docs/appearance/ai-features) states that there is no need to create new machine-readable files, AI text files or markup, and that there is no special structured data format to add. To appear, the page must be indexed and be eligible to be shown with a text snippet. Appearing is not guaranteed. The page shows no update date. - **Scope:** it applies to AI Overviews and AI Mode. It says nothing about other assistants, which have their own documentation. - **Evidence class:** official documentation. - **What is advisable instead:** the usual SEO practices that this same page recommends; see [what GEO is](https://cookingmetrics.com/blog/que-es-geo-generative-engine-optimization/). ## Myth 4: "llms.txt makes assistants cite the site more" - **What llms.txt is:** a proposal by Jeremy Howard, published in September 2024 and updated in August 2026 at [llmstxt.org](https://llmstxt.org/), to offer agents information that helps them use a site. Its author says he expected it to be useful mainly when the agent consults the site, rather than for training. The page claims no effect on rankings, citations or traffic. - **What the companies say:** we did not find official Google documentation saying that it reads it, and the Google page from myth 3 states that it is not needed. OpenAI's page on its crawlers does not mention llms.txt when describing them. We did not consult Anthropic documentation on the subject. - **What the only study consulted says:** SE Ranking, a company that sells SEO software, published on October 15, 2026 a [study of about 300,000 domains](https://seranking.com/blog/llms-txt/). Only 10.13% had the file. The study reports that there is no correlation between having it and being cited, and that removing that variable from its model improved its accuracy. The page does not state which assistants it consulted, how many answers, on which dates or the values of the correlations, and its authors warn that the results depend on the model and on the dataset. - **What can be concluded:** there is no evidence in favor of llms.txt increasing citations, and the only study consulted found no relationship. Nor is it definitive proof against: the study comes from a vendor, with an incomplete method on the page, and assistants change. The file may have other uses for those who develop agents, as its proposal indicates. Cloudflare, in its agent readiness evaluation, treats it as optional; see [what isitagentready.com measures](https://cookingmetrics.com/blog/que-mide-isitagentready/). - **Evidence class:** proposal by the format's author, absence from official documentation and a vendor study. ## Mixed evidence 5: "being in the top 10 ensures you get cited" This claim is neither a proven myth nor a truth. What exists are two Ahrefs studies, a company that sells SEO software, on Google AI Overviews: - **July 2025:** [76.10% of the cited pages](https://ahrefs.com/blog/search-rankings-ai-citations/) were among the first ten results, out of 1.9 million citations from 1 million AI Overviews, taking the first three citations of each answer. - **March 2026:** [37.9% of the cited addresses](https://ahrefs.com/blog/ai-overview-citations-top-10/) were among the first ten, out of 863,000 queries and 4 million addresses. The article itself compares "~76% versus ~38%", but states that it improved its analysis method; that is why it is not a direct comparison. The data come from the vendor's own visibility tool. Two corrections to the reading: - **It is a proportion of the cited pages**, not of the top 10 pages. That a share of the cited pages is in the top 10 does not say how many top 10 pages are cited. - **Both figures are from AI Overviews.** They do not apply to ChatGPT or AI Mode. In [the guide on query fan-out](https://cookingmetrics.com/blog/query-fan-out-que-es-como-cubrir-subconsultas/) another vendor study is discussed, according to which about two thirds of the cited pages were in the top 10 neither for the main query nor for any sub-query. The prudent statement is that ranking well helps in being considered, without a guarantee, and that the percentages vary with the method. ## Mixed evidence 6: "long content is cited more" An [Ahrefs study](https://ahrefs.com/blog/short-vs-long-content-in-ai-overviews/) from December 3, 2025 analyzed 560,346 AI Overviews and 1,677,876 cited addresses, and obtained a Spearman correlation of 0.04 between word count and citation: practically none. The article uses the same figure for being cited and for the position of the citation. The average cited page had 1,282 words; 53.4% had fewer than 1,000. A limitation pointed out by this guide, not by the study: the sample includes only cited pages. It does not compare with pages that were not cited, so it does not allow concluding whether length influences being cited or not. It is a vendor study, on AI Overviews, and there are no length data for ChatGPT in the materials read. The evidence is "no relationship observed in those data", not a rule. [Section for signed-in readers, level C: https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/#bloque-2] ## What to do instead CookingMetrics recommendation, not a guarantee: - **Secure the basics:** that pages are indexable, with content in the initial HTML and accessible to the robots you want to allow. See [what to look for in a web design and development provider](https://cookingmetrics.com/blog/que-buscar-proveedor-desarrollo-web/). - **Measure your own data:** visits, crawling and citations of your own site, before relying on third-party figures. - **Always ask about the source:** who says it, with what sample, what they sell, and whether it is official documentation or a vendor study. - **Treat mixed evidence as uncertainty:** test one change at a time and record the date, without attributing the result to it. [Section for signed-in readers, level C: https://cookingmetrics.com/blog/mitos-geo-que-dicen-fuentes-primarias/#bloque-3] ## What not to conclude - That a practice "does not work" because we found no official backing: it is an absence of documentation, not proof of the contrary. - That what is said about Google's AI features applies to other assistants. - That a vendor's correlation demonstrates causality. - That this list exhausts the GEO myths. ## What to do next For common claims about conventional search, see [what Google says about SEO myths](https://cookingmetrics.com/blog/mitos-seo-que-dice-google/). Before implementing a GEO recommendation, write in one line which source backs it and of what class it is. If you would like us to review which recommendations on your site have backing and how to measure their effect, learn about our [SEO for AI search service](https://cookingmetrics.com/services/seo-ai-geo/): we review and support your team, and we do not sell visibility tools. ## Frequently asked questions ### What is Common Crawl and why does it matter in GEO? It is a public collection of web pages that is used, among other things, to train models. Its documentation describes a crawl of a sample of the web. Being in that collection does not on its own explain a citation in an assistant with search. ### Do I need an llms.txt file to appear in AI Overviews? No. Google states that there is no need to create new files or AI text files to appear in AI Overviews or AI Mode. The file is a proposal designed for agents that consult a site. ### Does being in the top 10 guarantee that Google cites me in AI Overviews? No source guarantees it. The Ahrefs studies measure what proportion of the cited pages was in the top 10, with results of 76.10% and 37.9% depending on the version and the method, and not the probability of being cited when in the top 10. ### Is longer text cited more? An Ahrefs study on AI Overviews found no relationship between word count and citation (correlation of 0.04). It analyzed only cited pages, so it does not allow concluding about being cited or not. ### How do I tell a myth from a recommendation with backing? Ask who states it, with what sample, whether they sell something related and whether there is official documentation. If there is no primary source, it is a hypothesis; if the evidence comes from a vendor, it is an indication, not proof. --- ## About the author **[Martín Garay](https://cookingmetrics.com/about-martin-garay/)** — Founder of CookingMetrics I'm Martín Garay, founder and Martech Advisor at CookingMetrics and Chair of the Technology Committee at CACE, Argentina's ecommerce chamber. For more than 20 years I've worked in Analytics, development, technical SEO and ecommerce: I implement measurement, find where it breaks and turn it into information you can act on. ### My work at CACE, Argentina's ecommerce chamber - **Chair of the Technology Committee** (SINCE AUGUST 2025): I set the committee's agenda together with Gabriel Topola, vice-chair. We look at the platforms and tools an online business needs to grow: CMS, integrations, customer service and omnichannel operations. - **Curating the technical forum** (IT CAMP · ECOMMERCE DAY ARGENTINA): With CACE's Events team I put together the IT Camp programme: talks for engineering and development teams on platform architecture, code and good practice, given by speakers who do the implementation work. - **Marketing and Data Analytics committees** (SINCE 2016): I started in the Marketing committee and helped create the Data Analytics committee. I gave Google Analytics webinars, including the migration to GA4, and worked on the Google Analytics implementation for Hot Sale and Cyber Monday. - **Ecommerce metrics dashboard** (FOR MEMBERS): With the Data Analytics committee and the CACE Community team we built a dashboard in Google Analytics and Looker Studio so each member can check the key indicators of their own store. ### Talks - [From SEO to GEO: what it takes for a brand to be cited by an answer engine](https://www.youtube.com/watch?v=mlyjuSBdMzI) — ECOMMERCE DAY ARGENTINA 2026 · IT CAMP · AUGUST 27, 2026 · BUENOS AIRES CONVENTION CENTER - [SEO for AI: how to prepare a brand to show up in ChatGPT and Google's AI overviews](https://www.youtube.com/watch?v=4dI7jqnLg-M) — AI IN LATAM 2025 · BUENOS AIRES · OVER 3,500 ATTENDEES AND 100 SPEAKERS, PER THE ORGANIZERS ### Profiles and links - [Full profile](https://cookingmetrics.com/about-martin-garay/) - [LinkedIn](https://www.linkedin.com/in/seospecialistmartingaray/) - [Instagram](https://www.instagram.com/garaymartin/) - [YouTube](https://www.youtube.com/@MartinGaray) - [martingaray.com.ar](https://www.martingaray.com.ar/) - [Chair of the Technology Committee at CACE, Argentina's ecommerce chamber](https://cace.org.ar/pages/comision-de-tecnologia?utm_source=cookingmetrics.com&utm_medium=referral&utm_campaign=perfil-martin&utm_content=caja-autor) - [Ecommerce metrics dashboard, free for CACE members](https://cace.org.ar/pages/dashboard-de-metricas?utm_source=cookingmetrics.com&utm_medium=referral&utm_campaign=perfil-martin&utm_content=caja-autor) --- ## About CookingMetrics CookingMetrics provides Google Analytics consulting, measurement implementation and SEO. Founder Martín Garay brings more than 20 years of experience in Analytics, development and ecommerce. The work connects data with business decisions. ### Services - **[Google Analytics audit](https://cookingmetrics.com/data-analytics-consulting/)**: Do purchases or revenue differ from your store? We review your measurement and deliver a correction plan in 10 business days. [See the audit scope](https://cookingmetrics.com/data-analytics-consulting/). - **[Google Tag Manager](https://cookingmetrics.com/services/gtm/)**: Did events stop being tracked after a website change? We review tags, triggers and versions to find duplicates or missing data. [Ask about Google Tag Manager audits and implementation](https://cookingmetrics.com/services/gtm/). - **[Server-side measurement](https://cookingmetrics.com/services/cookieless-tracking/)**: We assess how to send data from your server, respect consent and prevent duplication. [What's included in server-side measurement](https://cookingmetrics.com/services/cookieless-tracking/). - **[Technical SEO](https://cookingmetrics.com/services/technical-seo/)**: Have you migrated your site, or are pages missing from Google? We review crawling, indexing, structure and performance. [How we approach technical SEO](https://cookingmetrics.com/services/technical-seo/). - **[SEO for AI search (GEO)](https://cookingmetrics.com/services/seo-ai-geo/)**: We review whether search engines and assistants can access your pages and understand their content. [What we can improve for AI search](https://cookingmetrics.com/services/seo-ai-geo/). ### Solutions - **[Google Analytics self-check](https://cookingmetrics.com/google-analytics-self-check/)** (Status: Available) - **[GA4 Report Generator](https://cookingmetrics.com/product/ga4-report-generator/)** (Status: Beta): A tool in beta that already generates Google Analytics reports. Ask about available features and the scope for your project. [Explore GA4 Report Generator](https://cookingmetrics.com/product/ga4-report-generator/). - **[IndexNow Connect](https://cookingmetrics.com/product/indexnow-connect/)** (Status: Available for Tiendanube): Notifies search engines participating in IndexNow of new, updated or deleted URLs. [How IndexNow Connect works](https://cookingmetrics.com/product/indexnow-connect/). - **[AI SEO Analysis](https://cookingmetrics.com/product/ai-seo-analysis/)** (Status: In development): *Coming soon.* An automated audit of how AI assistants and search engines access and use your content. [Learn about AI SEO Analysis](https://cookingmetrics.com/product/ai-seo-analysis/). **Let's talk about your measurement:** [Book a call](https://cookingmetrics.com/about-martin-garay/) · [CookingMetrics](https://cookingmetrics.com/)