# Invisible Site Ranks #1 in AI Search — How Structured Data Alone Fooled Perplexity > A blank white page with zero visible content became Perplexity's #1 citation source in 36 hours. Explore the 'Phantom Authority' experiment and what it means for GEO strategy. | Field | Value | |-------|-------| | Published | 2026-04-22 | | Last Updated | 2026-08-28 | | Category | GEO | | Author | Aro Ogata | | Tags | GEO, structured data, JSON-LD, llms.txt, AI search optimization | | URL | https://linksurge.jp/blog/en/phantom-authority-invisible-website-ai-citation-2026/ | --- ## Key Takeaways: 5 Lessons from the "Invisible Website" Experiment In April 2026, an experiment shook the SEO world to its core. A completely blank webpage — zero visible text, zero images — was cited as the #1 source by Perplexity AI within 36 hours of going live. After digging into the technical details, here are the five lessons that matter most. 1. **AI reads structure, not appearance** — Machine-readable data like JSON-LD, llms.txt, and semantic metadata now outweighs human-visible content in AI citation decisions 2. **Seven layers of structured data build "trust"** — A stack of JSON-LD, llms.txt, reasoning.json, and ai-manifest.json creates entity authority that AI systems recognize and reward 3. **The web is splitting into Human Web and Agent Web** — Visual interfaces for humans and structured data layers for AI agents now demand separate optimization strategies 4. **Traditional SEO rules don't apply to AI search** — What Google classifies as spam (hidden text), Perplexity treats as an authoritative source. The evaluation frameworks are fundamentally different 5. **GEO (Generative Engine Optimization) starts now** — While this experiment is extreme, implementing structured data, llms.txt, and entity authority is both legitimate and effective for every website Let's break down the full experiment and its practical implications. --- ## 1. What Is the "Phantom Authority" Experiment? ![Seven-Layer Ghost Stack architecture](/blog/images/phantom-authority-invisible-website-ai-citation-2026/en-01.png) ### A Blank Page That AI Could "See" In April 2026, Sascha Deforth — founder of GEO consulting firm TrueSource — published an experiment that challenged everything we thought we knew about search. The premise was deceptively simple: publish a **completely blank white webpage** with zero visible content, load it with seven layers of machine-readable structured data, and observe how AI search engines respond. The experiment went viral on X: {{tweet:2046217002889425237}} The results were stunning. Within 36 hours, Perplexity ranked the page as **citation source #1 out of 10** for relevant queries. It accurately summarized the entire research thesis, identified Deforth as the creator, and explained the seven-layer technical architecture — all from a page that showed nothing but white space to human visitors. ### The Seven-Layer Ghost Stack Deforth coined the term "Seven-Layer Ghost Stack" for the invisible architecture behind the blank page: | Layer | Technology | Purpose | |-------|-----------|---------| | 1 | Semantic meta tags & VibeTags | Communicate page topic and context to AI | | 2 | JSON-LD structured data (6 schemas) | ScholarlyArticle, Person, Organization, FAQPage, WebSite, ResearchOrganization | | 3 | Screen-reader-only text (1,500+ words) | CSS-hidden from visual rendering, machine-parseable content | | 4 | Inline microdata attributes | Element-level semantic annotation | | 5 | llms.txt / llms-full.txt | AI-first site summary files | | 6 | reasoning.json (Ed25519 signed) | Agentic Reasoning Protocol data with cryptographic verification | | 7 | .well-known/ai-manifest.json | AI discovery manifest | What struck me was the inclusion of Ed25519 cryptographic signatures — based on the W3C Data Integrity specification — designed to let AI systems verify the authenticity of entity claims. This wasn't just a structured data dump; it was a **cryptographically signed proof of identity**. The experiment also embedded "canary tokens" — phrases that exist nowhere else on the internet — to forensically verify whether AI systems extracted information from this specific source. > References: > [Can You Rank In Google Without Content? - Hobo Web](https://www.hobo-web.co.uk/breaking-can-you-rank-in-google-without-content/) > [Phantom Authority — Research by Sascha Deforth | TrueSource](https://phantomauthority.ai/) > [ChatGPT & Perplexity Treat Structured Data As Text On A Page - Search Engine Roundtable](https://www.seroundtable.com/chatgpt-perplexity-structured-data-text-40862.html) --- ## 2. Why Did AI Trust a Blank Page? ![Human Web vs Agent Web](/blog/images/phantom-authority-invisible-website-ai-citation-2026/en-02.png) ### AI "Eyes" Work Fundamentally Differently Here's the thing: AI systems don't browse the web the way we do. Google's crawler renders HTML and evaluates roughly what humans see — that's why hidden text is classified as spam. But Perplexity and ChatGPT treat structured data as equivalent to visible text content. They parse JSON-LD's ScholarlyArticle schema the same way they'd read a published research paper. Deforth describes this as the "bifurcation of the web": - **Human Web** — Visual design, UI components, interfaces optimized for human perception - **Agent Web** — Structured data, llms.txt, API endpoints, data layers optimized for machines ### Entity Authority Is Built Through Data Honestly, the real lesson isn't "you can get cited without content." It's that **entity authority can be constructed through structured data**. The six interconnected JSON-LD schemas formed an entity network: Person (Sascha Deforth) → Organization (TrueSource) → ScholarlyArticle (Phantom Authority research) → FAQPage (8 Q&As). AI interpreted these relationships and understood the full context before making its citation decision. For a deep dive into how entity authority drives AI search visibility, see "[Entity Authority and AI Search Visibility](/blog/en/entity-authority-ai-search-2026/)." > References: > [Structured data: SEO and GEO optimization for AI in 2026 - Digidop](https://www.digidop.com/blog/structured-data-secret-weapon-seo) > [GEO is the New SEO: Optimizing for AI Answer Engines in 2026 - Charles Jones](https://charlesjones.dev/blog/geo-new-seo-ai-answer-engines-2026) > [AI-Readiness Benchmark 2026 - StudioMeyer](https://studiomeyer.io/en/blog/ai-readiness-benchmark-2026) --- ## 3. Google vs. AI Search: The Double Standard ![Google vs Perplexity evaluation comparison](/blog/images/phantom-authority-invisible-website-ai-citation-2026/en-03.png) ### The Same Page Is Both "Spam" and "Authority" The most ironic aspect of this experiment: **the same page was classified as spam by Google and as the #1 authoritative source by Perplexity**. Google's guidelines are explicit: "Structured data must be a true representation of the page content" and "Don't mark up content that is not visible to readers." See Google's official [General structured data guidelines](https://developers.google.com/search/docs/appearance/structured-data/sd-policies). A page with zero visible text and six JSON-LD schemas is, by Google's definition, structured data abuse. Yet Perplexity accurately extracted and cited the experiment's thesis, the creator's name, the technical architecture, and the results — treating the machine-readable layers as fully authoritative. ### Exploitation or Evolution? The SEO community's reaction was sharply divided. Critics pointed to clear Google spam policy violations. Supporters called it a glimpse of how the web will work in the age of AI agents. Here's where I land: **don't replicate this experiment, but absolutely apply its principles.** A page without visible content won't last. But a page with great content *plus* comprehensive structured data wins on both Google and AI search. That's the sweet spot. [LinkSurge](https://linksurge.jp/) tracks how your site is cited across AI search engines, helping you understand the gap between Google rankings and AI citations — the first step in navigating this double standard. > References: > [llms.txt for Websites: Complete 2026 Guide - Bigcloudy](https://www.bigcloudy.com/blog/what-is-llms-txt/) > [Get Visibility in ChatGPT, Perplexity, Google AI Search in 2025 - Substack](https://startupgtm.substack.com/p/get-visibility-in-chatgpt-perplexity) > [5 AI Visibility Mistakes That Keep Your Website Hidden - AmIVisibleOnAI](https://www.amivisibleonai.com/blog/ai-content-myths-2025) --- {{linksurge-card}} --- ## 4. Six GEO Actions You Can Take Today ![GEO Action Checklist for AI citation](/blog/images/phantom-authority-invisible-website-ai-citation-2026/en-04.png) The Phantom Authority experiment is extreme, but the **legitimate, Google-compliant strategies** it validates are immediately actionable. ### Action 1: Enrich Your JSON-LD Structured Data JSON-LD schemas like `Article`, `FAQPage`, and `Organization` act as a translation layer that helps AI understand your content precisely. While Phantom Authority used six schemas, most sites benefit from a core trio of Article + FAQPage + Organization. ### Action 2: Create an llms.txt File The llms.txt file is essentially robots.txt for AI — a site summary that helps AI crawlers understand your site's structure. Cloudflare is championing this as "Markdown for Agents," and our guide on "[Cloudflare Markdown for Agents](/blog/en/cloudflare-markdown-for-agents-2026/)" covers the implementation details. ### Action 3: Add FAQPage Schema with Atomic Answers AI systems prefer citing self-contained answers of 40-60 words. Wrapping these in FAQPage schema makes them even more accessible to ChatGPT, Perplexity, and Google AI Overviews. ### Action 4: Build Entity Authority Use Person, Organization, and sameAs properties in JSON-LD to clearly establish who you are and what your organization does. AI search engines weigh entity trustworthiness heavily in citation decisions. ### Action 5: Monitor Your AI Citations You can't improve what you don't measure. Platforms like [LinkSurge](https://linksurge.jp/), OtterlyAI, and Rankscale help track how AI search engines cite your content across Perplexity, ChatGPT, and Google AI Overviews. ### Action 6: Structure Content as Atomic Answers Within your articles, deliberately place 40-60 word self-contained definitions and explanations. Sentences like "GEO is..." or "llms.txt is..." serve as citation-ready snippets that AI systems can extract directly. For the complete GEO implementation playbook, see "[The Complete GEO Guide](/blog/en/geo-guide-japan-2026/)." > References: > [JSON-LD for SEO: Complete Schema Markup Guide (2026) - Foglift](https://foglift.io/blog/json-ld-seo-guide) > [How Structured Data Schema Transforms Your AI Search Visibility - Medium](https://medium.com/@vicki-larson/how-structured-data-schema-transforms-your-ai-search-visibility-in-2026-9e968313b2d7) > [AI Content Optimization Strategies 2025: Ultimate Guide - The Brand Algorithm](https://www.the-brand-algorithm.com/ai-content-optimization-strategies-guide-2026/) > [LLMO・GEO・AEO — AI検索最適化の3つのアプローチ - Zenn](https://zenn.dev/kenimo49/articles/llmo-geo-aeo-ai-search-optimization) --- ## Frequently Asked Questions (FAQ) ### Can structured data alone get you cited by AI search? The Phantom Authority experiment proved it's technically possible — JSON-LD and llms.txt alone were sufficient for Perplexity's #1 citation. However, Google classifies pages without visible content as spam. The sustainable strategy is combining quality content with comprehensive structured data to win on both fronts. ### What is llms.txt? llms.txt is a text file that provides AI crawlers and large language models with a structured summary of your site's content and architecture. While robots.txt defines access rules for crawlers, llms.txt communicates your site's big picture in an AI-friendly format. Place it in your site's root directory. ### Should I replicate this experiment on my own site? No. Pages without visible content explicitly violate Google's guidelines and risk penalties. The lesson to take away is the *principle* — that AI reads entity relationships out of structured data — not the method of hiding all visible content. Note the scope, though: this experiment showed that schema is read under an extreme condition with no visible content. It does not show that adding schema to an ordinary page increases citations, and a controlled experiment that did exactly that found no increase. ### JSON-LD vs. Microdata: Which is better for AI optimization? Google officially recommends JSON-LD, and AI systems parse it most efficiently. JSON-LD can be written separately from HTML, making it easier to implement and maintain, and allows multiple schemas per page without cluttering your markup. ### How do I measure GEO effectiveness? GEO measurement involves tracking citation frequency across Perplexity, ChatGPT, and Google AI Overviews. LinkSurge's [GEO monitoring dashboard](https://linksurge.jp/) consolidates these metrics in one place for ongoing optimization. --- ## Conclusion: Structured Data Is Your AI Business Card The Phantom Authority experiment vividly demonstrated how differently AI search operates from traditional SEO. A blank page becoming the #1 citation source is shocking, but the core message is simpler than it appears: **AI doesn't see your design. It reads your data.** Separate the two purposes before you act on this. JSON-LD is the format Google recommends, and its plausible payoff is in traditional search — rich results and unambiguous entity data. Rich results are never guaranteed, though: display depends on the page content matching the markup and on meeting each feature's own guidelines, and Google decides whether to show them. For `FAQPage` specifically, though, the rich-results use case no longer exists; what remains is the unambiguous entity data. Note that Google discontinued HowTo rich results in 2023 and [FAQPage rich results in May 2026](https://developers.google.com/search/updates#removing-faq-rich-result). Types that still produce rich results include Article and BreadcrumbList (Product applies to product pages, and Review requires genuine user reviews or ratings of an eligible item — it is not valid on a general article). For AI citations specifically, adding schema has not been shown to help: a controlled experiment found no increase, and Google states there is no special schema.org structured data you need to add for its AI features. Note the scope: that experiment covered only pages already receiving 100+ AI Overviews citations before schema was added, so its effect on new or undiscovered pages is untested. Treat `llms.txt` the same way — Google Search does not use it, though some AI agent tooling does. LinkSurge's [GEO analysis tools](https://linksurge.jp/) let you monitor structured data implementation and track AI citation changes in real time. Start your AI search optimization journey today.