GeoHarness

Citations and evidence grades

Every claim GeoHarness relies on, in its design, its GEO score and this documentation, is listed here with an evidence grade. The audit's findings cite these ids, and a test fails if any id is missing.

Updated · Generated from CITATIONS.md

How are sources graded?

Grade A is peer-reviewed work or a primary platform specification; B a large-sample study with a published method; C a vendor log analysis or small sample; D commentary used for context only.

Evidence grades
GradeMeaning
APeer-reviewed, or a primary platform specification/documentation
BLarge-sample industry study with published method
CVendor log analysis or small-sample measurement
DCommentary or single observation; used for context only

Research papers

IDSourceGradeSupports
aggarwal-2024Aggarwal et al., "GEO: Generative Engine Optimization", KDD 2024. https://arxiv.org/abs/2311.09735 (accessed 2026-11-19)AOriginal GEO lab result: quotations, statistics and citations raise visibility inside a fixed retrieved context; keyword stuffing hurts. Scored as advisory only.
cseo-bench-2025"C-SEO Bench: Does Conversational SEO Work?", NeurIPS 2025 Datasets & Benchmarks. https://arxiv.org/abs/2506.11097 (accessed 2026-11-19)AMost content-rewrite methods are ineffective; classic SEO is more reliable. Why GeoHarness never rewrites prose.
sageo-2026"SAGEO Arena", KDD 2026. https://arxiv.org/abs/2602.12187 (accessed 2026-11-19)AStructural information helps retrieval and reranking; several GEO methods hurt it.
martinez-2026Martinez, survey of 45 GEO studies, arXiv 2607.14035 (2026). https://arxiv.org/abs/2607.14035 (accessed 2026-11-19)B (preprint)No technique shows a stable cross-platform causal effect; relevance and position are the reproducible levers. Basis for weighting access and extractability above content heuristics.
what-gets-cited-2026"What Gets Cited", arXiv 2605.25517 (2026). https://arxiv.org/abs/2605.25517 (accessed 2026-11-19)B (preprint)Relevance and list position dominate; explicit price and a recent timestamp help; formatting-only edits barely matter. Basis for the visible-date check.
htmlrag-2025Tan et al., "HtmlRAG", WWW 2025. https://arxiv.org/abs/2411.02959 (accessed 2026-11-19)AKeeping structure (headings, tables) beats flattening to plain text. Why markdown twins keep tables and headings.
cormack-2009Cormack, Clarke and Büttcher, "Reciprocal Rank Fusion outperforms Condorcet and individual rank learning methods", SIGIR 2009. https://doi.org/10.1145/1571941.1572114 (accessed 2026-11-19)ARRF with k = 60, used for LatticeDB hybrid search.
robertson-2009Robertson and Zaragoza, "The Probabilistic Relevance Framework: BM25 and Beyond", Foundations and Trends in IR, 2009. https://doi.org/10.1561/1500000019 (accessed 2026-11-19)ABM25 scoring and the k1/b constants used by LatticeDB's lexical index.

Industry studies

IDSourceGradeSupports
ahrefs-schema-2026Ahrefs, "We Tracked 1,885 Pages Adding Schema. AI Citations Barely Moved", May 2026. https://ahrefs.com/blog/schema-ai-citations/ (accessed 2026-11-19)BJSON-LD gave no significant AI-citation lift. GeoHarness emits minimal JSON-LD for classic search only.
ahrefs-llmstxt-2026Ahrefs, "We Analyzed 137K Sites: 97% of llms.txt Files Never Get Read", June 2026. https://ahrefs.com/blog/llmstxt-study/ (accessed 2026-11-19)Bllms.txt is rarely fetched, mostly by coding agents. Generated because it is free, scored as speculative.
seranking-llmstxt-2026SE Ranking, "LLMs.txt: Why Brands Rely On It and Why It Doesn't Work", 2026. https://seranking.com/blog/llms-txt/ (accessed 2026-11-19)BNo correlation between llms.txt and AI citations across ~300K domains.
peec-reading-budget-2026Peec AI, "Deep Research reading budget", June 2026. https://docs.peec.ai/research/deep-research-reading-budget.md (accessed 2026-11-19)CFirst read covers ~78% of content on pages with fewer than 20 links and ~33% with 60 or more; ~5.7K-character first window. Basis for the link-density and front-loading checks (advisory).
peec-how-deep-research-reads-2026Peec AI, "How Deep Research reads your site", 2026. https://docs.peec.ai/research/how-deep-research-reads-your-site.md (accessed 2026-11-19)CAgents read text only and re-read after an in-page match. Basis for the empty-SPA-shell check.
indig-2026Kevin Indig, "The science of how AI picks its sources", Growth Memo, Feb 2026. https://www.growth-memo.com/p/the-science-of-how-ai-picks-its-sources (accessed 2026-11-19, paywalled)C44.2% of ChatGPT citations come from the first 30% of a page. Sometimes misattributed to SparkToro.
checkly-2026Checkly, "State of AI agent content negotiation", Feb 2026. https://www.checklyhq.com/blog/state-of-ai-agent-content-negotation/ (accessed 2026-11-19)CWhich agents send Accept: text/markdown (Claude Code, Cursor, OpenCode) and which do not.
evilmartians-2026Evil Martians, "Which AI actually reads your site: two months of LLM traffic measured", 2026. https://evilmartians.com/chronicles/which-ai-actually-reads-your-site-two-months-of-llm-traffic-measured (accessed 2026-11-19)CClaude Code received markdown 88% of the time; ChatGPT-User 0.7%.

Platform documentation and specifications

IDSourceGradeSupports
google-ai-guide-2026Google Search Central, "AI features and your website" optimization guide, May 2026. https://developers.google.com/search/docs/fundamentals/ai-optimization-guide (accessed 2026-11-19)AGenerative features rest on core Search eligibility; markdown/AI text files are neither required nor used by Google Search.
google-spam-policiesGoogle Search Central, "Spam policies: cloaking". https://developers.google.com/search/docs/essentials/spam-policies (accessed 2026-11-19)AWhy GeoHarness negotiates on Accept, never on search-crawler user agents, and checks markdown/HTML equivalence.
llmstxt-specllms.txt proposal. https://llmstxt.org/ (accessed 2026-11-19)A (spec)llms.txt format; per-page .md convention; rel="alternate" type="text/markdown".
cf-content-signalsCloudflare, "Content Signals Policy". https://blog.cloudflare.com/content-signals-policy/ (accessed 2026-11-19)A (spec)Content-Signal: search, ai-input, ai-train in robots.txt and headers.
cf-markdown-for-agentsCloudflare docs, "Markdown for Agents". https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/ (accessed 2026-11-19)APlan availability (Pro+), headers (Vary: Accept, Content-Signal), 6 MiB limit; GeoHarness reproduces this for free.
cf-transform-rulesCloudflare docs, Transform Rules availability and URL Rewrite parameters. https://developers.cloudflare.com/rules/transform/ and https://developers.cloudflare.com/rules/transform/url-rewrite/reference/parameters/ (accessed 2026-11-19)A10 free rules, concat and wildcard_replace on all plans, no regex on Free.
cf-rules-functionsCloudflare docs, Rules language functions and header fields. https://developers.cloudflare.com/ruleset-engine/rules-language/functions/ (accessed 2026-11-19)AMatching http.request.headers["accept"].
cf-phasesCloudflare docs, Ruleset Engine phases list. https://developers.cloudflare.com/ruleset-engine/reference/phases-list/ (accessed 2026-11-19)ATransform runs before cache.
cf-workers-static-assetsCloudflare docs, Workers static assets billing, routing, headers. https://developers.cloudflare.com/workers/static-assets/ (accessed 2026-11-19)AFree unlimited asset requests, run_worker_first, _headers (100 rules).
cf-workers-limitsCloudflare docs, Workers platform limits. https://developers.cloudflare.com/workers/platform/limits/ (accessed 2026-11-19)A100k requests/day, 10 ms CPU, 128 MB memory on Free.
cf-pages-limitsCloudflare docs, Pages limits and Functions pricing. https://developers.cloudflare.com/pages/platform/limits/ (accessed 2026-11-19)APages Functions share the Workers quota; fail-open option.
cf-workers-aiCloudflare docs, Workers AI pricing and OpenAI-compatible embeddings. https://developers.cloudflare.com/workers-ai/ (accessed 2026-11-19)A10k free neurons/day; embedding models and dimensions.
cf-bot-fight-modeCloudflare docs, Bot Fight Mode and verified bots. https://developers.cloudflare.com/bots/get-started/bot-fight-mode/ (accessed 2026-11-19)AWhy GeoHarness turns it off and verifies AI bots get HTTP 200.
cf-managed-robotsCloudflare docs, managed robots.txt and AI crawler policies. https://developers.cloudflare.com/bots/additional-configurations/managed-robots-txt/ (accessed 2026-11-19)AAI crawler policy defaults.
cf-speedCloudflare docs, Early Hints, Speed Brain, Tiered Cache, Compression Rules. https://developers.cloudflare.com/speed/ (accessed 2026-11-19)AFree speed settings GeoHarness enables.
cf-api-permissionsCloudflare docs, API token permissions. https://developers.cloudflare.com/fundamentals/api/reference/permissions/ (accessed 2026-11-19)Acloudflare-permissions.json.
indexnowIndexNow documentation. https://www.indexnow.org/documentation (accessed 2026-11-19)A (spec)Key file and submission endpoint.
openai-botsOpenAI, "Overview of OpenAI crawlers". https://developers.openai.com/api/docs/bots (accessed 2026-11-19)AGPTBot, OAI-SearchBot, ChatGPT-User tokens.
anthropic-botsAnthropic, "Does Anthropic crawl data from the web". https://support.claude.com/en/articles/8896518-what-is-claudebot (accessed 2026-11-19)AClaudeBot, Claude-SearchBot, Claude-User tokens.
perplexity-botsPerplexity, "Perplexity crawlers". https://docs.perplexity.ai/guides/bots (accessed 2026-11-19)APerplexityBot, Perplexity-User tokens.
qdrant-query-apiQdrant docs, hybrid queries, sparse vectors, inference. https://qdrant.tech/documentation/concepts/hybrid-queries/ (accessed 2026-11-19)ARequest shapes LatticeDB's text, sparse and fusion queries follow.

Tools and prior art

IDSourceGradeSupports
markdown-newmarkdown.new. https://markdown.new/ (accessed 2026-11-19)DPrior art: three-tier HTML-to-markdown conversion, x-markdown-tokens, vary: accept.
geo-newGEO.new. https://geo.new/ (accessed 2026-11-19)DPrior art: category weights for a GEO audit (AI Citability 22%, Content/E-E-A-T 22%, Brand/Entity 20%, AI Access 15%, Schema 13%, Platform 8%).
lighthouse-ciGoogle, Lighthouse CI. https://github.com/GoogleChrome/lighthouse-ci (accessed 2026-11-19)AThe Lighthouse gate.
htmdhtmd crate. https://crates.io/crates/htmd (accessed 2026-11-19)AHTML-to-markdown engine.
lol-htmlCloudflare lol_html. https://github.com/cloudflare/lol-html (accessed 2026-11-19)AStreaming head injection and link rewriting.

Rejected sources

Cited in research GeoHarness was given, checked, and not relied on.

ClaimWhy rejected
"Bajemon and Rochet (Sept 2026)" re-evaluation of GEO tacticsNo such paper could be found.
"SparkToro, January 2026: 44.2% of citations from the first 30% of a page"The figure is Kevin Indig's (see indig-2026), not SparkToro's.