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.
-
100% Citation Rate. 15/100 Entity Signals. What That Gap Actually Means.
Read more →: 100% Citation Rate. 15/100 Entity Signals. What That Gap Actually Means.GEO Lab Console audit reveals how a page with 100% citation rate can score just 15/100 on entity signals. The gap between retrieval and representation accuracy explained.
-
Moz Scores 3.7 on Perplexity — GEO Brand Citation Index
Read more →: Moz Scores 3.7 on Perplexity — GEO Brand Citation IndexMarch 2026 GEO Brand Citation Index results: Moz scores 3.7 on Perplexity while ChatGPT gives it 47.6. The delta between AI memory and live web reality reveals which brands are…
-
GEO Experiment 001: Declarative vs Narrative Structure
Read more →: GEO Experiment 001: Declarative vs Narrative StructureDeclarative content was cited in 18 of 30 queries (60.0%) versus 11 of 30 (36.7%) for narrative on Perplexity (z = 1.81, p = 0.07). A 23.3-percentage-point gap from structure…