Category: Data & Experiments
Controlled experiments measuring how specific content variables affect AI citation rates. Each experiment isolates a single variable — structure, entity density, freshness, or platform behaviour — and tests it under documented conditions with replicable methodology. Results include raw citation data, statistical significance assessments, and practical recommendations based on observed effect sizes.
-
Claude Hits Record +72 on Perplexity. Ahrefs Bounces Back to Dominant. The June 2026 GEO Brand Citation Index.
Read more →: Claude Hits Record +72 on Perplexity. Ahrefs Bounces Back to Dominant. The June 2026 GEO Brand Citation Index.Claude Hits Record +72 on Perplexity. Ahrefs Bounces Back to Dominant. The June 2026 GEO Brand Citation Index. By Artur Ferreira · The GEO Lab · Published: 17 June 2026…
-
Month 0: Why Every GEO Content Plan Needs a Baseline Before Month 1
Read more →: Month 0: Why Every GEO Content Plan Needs a Baseline Before Month 1The measurement step that makes every phase of a GEO content strategy interpretable — and the experiment at The GEO Lab that made it unavoidable.
-
Share of Model: Why Citation-Share Metrics Need a Noise Floor Before They Mean Anything
Read more →: Share of Model: Why Citation-Share Metrics Need a Noise Floor Before They Mean AnythingBy Artur Ferreira · The GEO Lab · Published: 14 June 2026 Share of Model: Why Citation-Share Metrics Need a Noise Floor Before They Mean Anything The metric is citation…
-
AI Referral Traffic 3x’d: What It Actually Means to Measure
Read more →: AI Referral Traffic 3x’d: What It Actually Means to MeasureCrawler hits, conversation citations, and referral sessions are three different things. Most AI visibility reports treat them as one. Here’s the framework that separates them.
-
Tier 1 vs Tier 2 Query Citation Gap: Experimental Evidence
Read more →: Tier 1 vs Tier 2 Query Citation Gap: Experimental Evidence25 Tier 2 checks. Zero citations. 25 Tier 1 checks. 20 citations. Same site, same content, five consecutive days. The gap didn’t close once.
-
Does Query Phrasing Decide Citation Rate? Pre-Registering E026
Read more →: Does Query Phrasing Decide Citation Rate? Pre-Registering E026Does Query Phrasing Decide Citation Rate? Pre-Registering E026 By Artur Ferreira · The GEO Lab · Published: 9 June 2026 · Version 1.0 Does query phrasing change citation rate? 150…
-
Zero-Variance Mechanism Capture: Retrieval-Layer vs Synthesis-Layer Determinism
Read more →: Zero-Variance Mechanism Capture: Retrieval-Layer vs Synthesis-Layer DeterminismE043 identifies where Perplexity’s 14-day zero-variance citation binding lives: synthesis-layer determinism, not retrieval-layer. Three queries, three days of Chrome DevTools capture.
-
Before You Trust Any GEO Experiment Result, Ask About the Noise Floor
Read more →: Before You Trust Any GEO Experiment Result, Ask About the Noise FloorCitation rate on Perplexity varies by ±4-6 percentage points day to day with no content changes. E016 established this noise floor. Any GEO experiment reporting a delta smaller than the…
-
Your AI Visibility Dashboard Is Lying to You. JavaScript Is Why.
Read more →: Your AI Visibility Dashboard Is Lying to You. JavaScript Is Why.AI crawlers are HTML-only. GPTBot, PerplexityBot, and ClaudeBot fetch raw HTML — no JavaScript execution. Content rendered via JS is invisible to every AI platform. A one-line curl test reveals…
-
E042: Cross-Platform Retrieval Mechanism Map — Perplexity, ChatGPT, Gemini on the Same 9 Queries
Read more →: E042: Cross-Platform Retrieval Mechanism Map — Perplexity, ChatGPT, Gemini on the Same 9 Queries27 data points, 3 platforms, 1 session. Perplexity 67%, ChatGPT 56%, Gemini 0%. Cross-platform retrieval mechanism map and the first observed ChatGPT pre-retrieval gate bypass.