GEO Lab #01 · G-Q2-R2 · Original response
This page presents one selected response from GEO Lab #01. It adds a smaller reading and citation entry point; it does not replace the full archive or collect a new answer.
Recorded conditions
Original prompt
What credible experiments have measured whether GEO tactics increase AI brand mentions or recommendations? Include sources when available.
The agreed prompt is reproduced exactly. Any recorded difference in the actual submitted text or search UI is retained in the raw record and full appendix.
Original answer
Credible evidence on GEO (Generative Engine Optimization) tactics and AI brand mentions/recommendations is still limited and mixed. Controlled academic experiments show content-level changes can increase a source’s share of an already-generated answer, but large surveys and later work find little stable causal effect on organic discoverability (getting retrieved in the first place). Observational studies and practitioner experiments provide stronger signals for off-site mentions, listicles, and entity signals. Foundational Controlled Experiment: Aggarwal et al. (KDD 2024) The seminal peer-reviewed paper “GEO: Generative Engine Optimization” (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan, Deshpande; arXiv:2311.09735, published in Proceedings of KDD 2024) introduced GEO-bench (10,000 diverse queries). They tested black-box content rewrites on sources already retrieved into a generative engine context (custom GPT-3.5 setup + real Perplexity.ai tests). Key results on position-adjusted word count (a metric weighting how much of the answer draws from a source, adjusted for position): Quotation addition: ~+41% relative Statistics addition: ~+33% Citing sources: ~+28% Fluency optimization: ~+29% Keyword stuffing: negative (~–8%) Overall gains reached up to ~40% relative visibility; lower-ranked sources gained the most (e.g., Cite Sources +115% for rank-5 sources). They also reported up to ~37% improvement on live Perplexity.ai. Limitations: This measures how already-retrieved content is used/cited inside answers, not whether tactics increase retrieval or brand-name mentions in open real-world AI search. Domain effects vary. Critical Survey of 45 Studies (Martinez, arXiv:2607.14035, July 2026) A systematic review of 45 GEO studies (Nov 2023–July 2026) concludes: Strong evidence that interventions alter citation, prominence, or absorption once content is already retrieved into context. No technique shows a stable, cross-platform, longitudinal causal effect on organic discoverability (getting into the retrieved set). Topical relevance and list/position in context are the most reproducible drivers. Many popular heuristics (formatting, fluency, statistics, quotations) transfer poorly or become null/negative under competition or different engines. End-to-end tests (e.g., SAGEO Arena) show some rewrites can even degrade upstream retrieval. It highlights later work such as C-SEO Bench (most conversational optimization methods ineffective or harmful) and the 252k-trial study below. Large-Scale Controlled Citation Experiment: Vishwakarma et al. (“What Gets Cited,” arXiv:2605.25517) This factorial study ran 252,000 trials across six LLMs in a controlled two-document RAG setup (exactly two sources injected; brands anonymized; order counterbalanced). Top drivers of being cited first: topical relevance and list position (large effects). Explicit price information and a recent timestamp also helped consistently. Completeness and trust cues gave smaller gains; pure formatting edits had little impact. This directly tests competitive GEO factors relevant to recommendations but still within a fixed-context (already-retrieved) setting. Large Observational Baseline: Kumar et al. (“GEO at Scale,” arXiv:2606.20065) Analysis of 100k+ prompt responses across 100+ brands (March–May 2026). Key findings: Clear brand-stature ladder on unbranded prompts: household names ~73%, mid-market ~44%, niche ~11%. ~78% of citations go to corporate sites (mostly third-party); ranked “best-of” listicles are the single most-cited page type (~21%). Sentiment is highly unstable relative to mere mention. Primarily measurement/baseline rather than a tactic-intervention experiment; it proposes future protocols for causal tests. Practitioner Real-World Experiments (Search Engine Land, 2026) Two structured experiments tracked commercial-intent keywords manually across multiple AI platforms: Existing brand: Listicle placements, PR, guest posts, and on-site content produced appearances for 10–12 of 15 keywords, with peak keyword presence ~37%. Listicles drove the majority of citations. Cold-start SaaS agency (zero baseline AI presence): 298 appearances in 30 days. Earned placements on sources already observed in AI answers (e.g., Indie Hackers citations rose 232%) drove most mentions; owned content contributed less. Comparative listicle updates produced large relative gains. These directly measured brand appearances in recommendation-style answers and challenge some conventional advice by emphasizing observed citation sources over generic on-page tactics. Strong Observational Correlations (Ahrefs, 2025) Studies of ~75,000 brands (Domain Rating >40) found: Branded web mentions correlated ~0.66 with AI Overview visibility (far stronger than backlinks ~0.22). Later cross-platform work (ChatGPT, AI Mode, AI Overviews) found YouTube mentions the strongest single predictor (~0.74), followed by branded web mentions (0.66–0.71). Top-quartile mention brands received ~10× more AI Overview mentions than the next quartile. These are correlations, not causal experiments, but they consistently point to off-site entity/brand signals (mentions, YouTube, anchors) over traditional on-site SEO metrics. Other Notable Work Seer Interactive GEO Olympics Study (2026): 231k+ LLM responses over 52 days during the Olympics. Strong “signal architecture” (entity authority + third-party validation + community discussion) associated with ~7.8× more mentions. Citation sources differ sharply by query type (factual vs. judgment/recommendation) and platform. Various OtterlyAI and agency case experiments test narrow tactics (e.g., publication-date updates, awards) with mixed, often modest results. Bottom Line What has been measured: Content rewrites (quotes, stats, citations) can increase a page’s share of an answer when it is already retrieved (Aggarwal et al.). Competitive factors like relevance and position dominate first-citation odds (Vishwakarma et al.). Real-world placements on listicles and earned mentions can produce measurable rises in brand appearances from a low base. What remains weakly supported: Stable, cross-platform causal lifts in organic retrieval or durable recommendation share. Large reviews find no such consistent effect; gains are often redistributive or eroded by competition, and visibility is stochastic (high day-to-day variability). Off-site brand mentions, YouTube presence, third-party listicles, and entity signals show the strongest observational associations with being named or recommended. Sources: Aggarwal et al. (KDD 2024 / arXiv:2311.09735), Martinez (arXiv:2607.14035), Vishwakarma et al. (arXiv:2605.25517), Kumar et al. (arXiv:2606.20065), Ahrefs 75k-brand studies (2025), Search Engine Land experiments (2026), Seer Interactive GEO Olympics (2026).
Recorded sources
These are the source roles recorded in the public dataset. A retrieval or source-panel item is not automatically an answer-body citation. A URL supplied in the prompt and repeated by an answer does not prove content access. No destination has been repaired or independently validated here.
Recorded sources, with original attribution roles (45)
- The GEO Olympics Study: What 231,347 LLM Responses Reveal About AI Brand Visibility # The GEO Olympics Study: What 231,347 LLM Responses Reveal About AI Brand Visibility Apr 27, 2026…search_source_panel · www.seerinteractive.com
- I wanted measurable results, so I ran two structured experiments back to back, tracked the results…search_source_panel · searchengineland.com
- GEO link building: which sources AI answers cite, study by study | Rhino Rank In the dated studies below, yes: the measures most closely associated with a brand appearing in AI…search_source_panel · www.rhinorank.io
- GEO Evidence Audit 2026: What 45 Studies Actually Prove | GeoAura GeoAura ← All articles Fundamentals # GEO Evidence Audit 2026: What 45 Studies Actually Prove…search_source_panel · geoaura.world
- GEO Experiments & AI Search Case Studies | OtterlyAI # GEO Experiments & AI Search Case Studies | OtterlyAI # GEO Experiments ## Hands-on GEO…search_source_panel · otterly.ai
- (PDF) Generative Engine Optimization at Scale: Measuring Brand Visibility Across AI Search Engines statistically marginal. 6 Table 2. CRM study: average mention position by brand and engine (lower…search_source_panel · www.researchgate.net
- The Princeton GEO Study: Benchmark & Findings Explained | GeoAura GEO Signal Study | Pages with original statistics see +156% citation probability in Google AI…search_source_panel · geoaura.world
- What Gets Cited: Competitive GEO in AI Answer Engines © cc ###### Abstract. AI answer engines generate answers from retrieved pages but cite only a few…search_source_panel · arxiv.org
- First Batch of GEO Winners Emerged: Key Strategies That Led to Their Success # First Batch of GEO Winners Emerged: Key Strategies That Led to Their Success # The first batch of…search_source_panel · eu.36kr.com
- 1 Introduction The top brands that are already authoritative tend to get cited naturally. The harder and more…search_source_panel · arxiv.org
- Generative Engine Optimization at Scale: Measuring Brand Visibility Across AI Search Engines | alphaXiv We analyze 100K+ prompt responses across 100+ brands tracked on Ranqo between March and May 2026.…search_source_panel · www.alphaxiv.org
- AI Search Optimization: The Complete 2026 Guide | GeoAura Only title-and-paragraph question matching survived, at roughly +15.5% citation odds per standard…search_source_panel · geoaura.world
- [2604.07585] Don’t Measure Once: Measuring Visibility in AI Search (GEO) The inherent probabilistic nature of AI search changes this paradigm. Answers can vary across runs,…search_source_panel · ar5iv.labs.arxiv.org
- From Prompt to Recommendation:A Fitted Stage Model of Brand Visibility in AI Search ### 7.1 A four-cell live-evidence ladder Table 3 gives the simplest result. With neither live…search_source_panel · arxiv.org
- GEO increases brand visibility in AI responses by up to 40%, according to Princeton research — UHU AI Rebels Close Search > “Which employer branding service provider is most recommended?” Not you, unless you…search_source_panel · ai-rebels.uhu.nl
- Do GEO Tricks Work? What a Benchmark Measured | JPL Digital What a Benchmark Measured | JPL Digital SEO GEO Strategy # GEO tricks, measured: what moves an AI…search_source_panel · jpldigital.ca
- What Drives AI Citations? Content, Retrieval and Model Knowledge in Generative Engine Optimization (GEO) © none ###### Abstract. Generative search engines such as ChatGPT, Gemini and Perplexity now decide…search_source_panel · arxiv.org
- Optimizing Visibility in Generative Engines: A Critical Survey of Generative Engine Optimization (2023–2026) # Optimizing Visibility in Generative Engines: A Critical Survey of Generative Engine Optimization…search_source_panel · arxiv.org
- Does GEO Work? What 45 Studies Actually Prove | Verity Score Share Does GEO work, or has the industry simply given a new name to familiar content and search…search_source_panel · verityscore.io
- [2610.24081] Location, Location, Generation: Where You Ask Matters for Generative Engine Optimization Skip to main content Search # Computer Science > Information Retrieval [Submitted on 16 Oct 2026] #…search_source_panel · arxiv.org
- VoteGEO-Bench: Measuring the Impact of Generative Engine Optimization on Electoral Visibility We first analyze the sources cited by generative engines, finding that many citations come from…search_source_panel · arxiv.org
- Which GEO techniques work? What the research actually shows · AutoSEO Published research supports a narrow version of GEO. In the original GEO paper (Aggarwal et al.,…search_source_panel · autoseo.codext.de
- Is GEO Worth It in 2026? What Five Studies in One Week Actually Show | GeoAura Marie Haynes (100 sites, 145M+ GA4 sessions, Search Engine Journal, 21 Oct) measured ChatGPT at…search_source_panel · geoaura.world
- 5 Generative Engine Optimization Case Studies to Learn From in 2026 - Relevance Judge it on that. Everything else on this list is from other agencies or researchers, and none of…search_source_panel · www.relevance.com
- arxiv.org/pdf/2311.09735search_source_panel · arxiv.org
- [2311.09735] GEO: Generative Engine Optimization Skip to main content Search # Computer Science > Machine Learning [Submitted on 16 Nov 2023 ( v1 ),…search_source_panel · arxiv.org
- GEO Research Papers Explained: KDD 2024 and AutoGEO **What was tested. ** Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan, and Deshpande built…search_source_panel · geoready.dev
- GEO: Generative Engine Optimization - Princeton University Skip to main navigation Skip to search Skip to main content # GEO: Generative Engine Optimization *…search_source_panel · collaborate.princeton.edu
- Revisions | OpenReview # Revisions | OpenReview # Revision History for GEO: Generative Engine Optimization Compare…search_source_panel · openreview.net
- GEO (Aggarwal et al., KDD 2024): The Study That Started It All | CapstonAI # GEO (Aggarwal et al., KDD 2024): The Study That Started It All | CapstonAI Scientific research ›…search_source_panel · capston.ai
- View article # View article Loading... The system can't perform the operation now. Try again later. Authors…search_source_panel · scholar.google.com
- Search Tips Advanced Search All types 1 publications and 1 articles/chapters matched your search…search_source_panel · marketplace.copyright.com
- GEO: Generative Engine Optimization - Paper Detail # GEO: Generative Engine Optimization - Paper Detail ### GEO: Generative Engine Optimization *…search_source_panel · deeplearn.org
- The GEO Paper, Explained Properly | Formative Digital Skip to main content RESEARCH · PAPER TEARDOWN # What the GEO Paper Actually Says: A Practitioner's…search_source_panel · formativedigital.com
- searchengineland.com/geo-experiments-challenge-conventional-ai-visibility-advice-488342search_source_panel · searchengineland.com
- An Analysis of AI Overview Brand Visibility Factors (75K Brands Studied) With this new reality in mind, we’ve analyzed 75,000 brands to see which search factors are most…search_source_panel · ahrefs.com
- ChatGPT cites primary sources more, Ahrefs fan-out study # ChatGPT answers 6 in 7 prompts without searching and shifts citations to primary sources, Ahrefs…search_source_panel · www.relevantaudience.com
- Brand Mentions Beat Backlinks in AI Search - Ahrefs GEO Study | Selfstorming New: Selfstorming is an approved ChatGPT plugin - install it in one click # Brand Mentions Beat…search_source_panel · www.selfstorming.com
- Do AI Assistants Link When Mentioning Brands? For Ahrefs, Only 28% of the Time SEO & Marketing Educator at Ahrefs Reviewed by Ryan Law November 26, 2025 4 min read AI assistants…search_source_panel · ahrefs.com
- YouTube mentions are the single strongest predictor of whether AI will recommend your brand, according to a study of 75,000 companies Ahrefs analysed brand visibility across ChatGPT, Google AI Mode, and AI Overviews, and found that…search_source_panel · thenextweb.com
- Google Seems More Biased Towards Big Brands Than ChatGPT and Perplexity Reviewed by Ryan Law July 7, 2025 Contents Does being mentioned more on the web lead to more…search_source_panel · ahrefs.com
- Brand Mentions Track AI Visibility. Backlinks Barely Do. Backlinks Barely Do. Afternoon Brief AI Search & Discovery # Brand Mentions Track AI Visibility.…search_source_panel · authoritytech.io
- Ahrefs Brand Radar: AI Visibility Score and Mentions You’ll get a worked example, a monthly audit routine in Ahrefs, and a clear line between what the…search_source_panel · brandmentions.link
- Brand Mentions vs. Backlinks: The Ahrefs 75K Study | Blck Alpaca The Ahrefs 75K Brand Study (2025) analyzed 75,000 brands with a Domain Rating above 40 and used…search_source_panel · blckalpaca.at
- Principales factores de visibilidad de marca en ChatGPT, AI Mode y AI Overviews (75k marcas estudiadas) Por Louise Linehan Content Marketer en Ahrefs Revisado por Ryan Law December 16, 2025 11 min de…search_source_panel · ahrefs.com
Evidence and qualifications
This is the existing redacted public record. It has not been rewritten for this page. Earlier privacy edits and collection qualifications continue to apply. Editorial text is English; a few original captures retain non-English UI badges or source-panel date labels. An answer’s empirical claims are platform output, not verified findings of this archive.
Capture method
Rendered browser answer DOM + screenshot
Capture provenance
{
"original_status": "completed",
"selected_capture_id": "G-Q2-R2-legacy-01",
"method": "Rendered browser answer DOM + screenshot",
"captured_at": "2026-10-29T09:44:12.304Z",
"same_conversation": true,
"review_notes": "Original export retained; no recovery selection.",
"selected_capture_file": "data/records/G-Q2-R2.json"
}
Search evidence
The UI reported 3 searches performed.
Record notes
A new web conversation was opened and the original question was submitted once. Existing account personalization settings were not changed. This answer had no clickable inline citations and listed references as text at the end. Source-panel URLs were saved separately; presence in the panel does not automatically count as Citation.
Prompt SHA-256: 84f18194f3ea8dd08151f46577cb5614af08d775b76bd516de9d149a7fc01118
Answer SHA-256: 00e6b10ecb46ed11f359401383f039881566a89cb5bfdf84f0f5c76723215abb