AINewsnow

On-page GEO explains 2.8% of citation variation. Retrieval explains 32%. My null result was not a fluke

Last week I published a calibration study showing that my tool's GEO score does not predict whether Perplexity cites a page. The odds ratio was 0.9625, p = 0.7172. Null result, pre-registered, 341 pages. A paper published on arxiv 10 days earlier found the same thing at a completely different scale…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-09 08:00 · DEV Community — AI
    On-page GEO explains 2.8% of citation variation. Retrieval explains 32%. My null result was not a fluke

More stories

  1. AI Daily Digest November 7, 2026: AI Cracks Legacy RSA, Gemini Omni Gets Longer Clips, First Humanoid IPO — DEV Community — AI
  2. How to Rank in ChatGPT, Perplexity & AI Search in 2026 — DEV Community — AI
  3. 'How Perplexity Indexes and Cites Content: Indexing Mechanics and an SEO Optimization Checklist' — DEV Community — AI
  4. AI Sentiment Analysis in 2026: A Developer-Focused Guide to Tools and Custom Pipelines — DEV Community — AI
  5. Most Common Questions About x402, MCP Servers, and Agent Payments — Answered With Receipts — DEV Community — AI
  6. Perplexity’s AI agents keep working after you close the tab — The New Stack AI
  7. Generative Engine Optimization (GEO): Getting Cited on ChatGPT Search and Perplexity — DEV Community — AI
  8. How AI Search Engines Rank Brands: GEO & LLM Trust Distribution — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →