GEO paper — visibility improvements up to 37% on Perplexity.ai (live engine, 200-sample test)

reference · Scope: business · Status: current

ai-citation llm-answer-engines generative-engine-optimization

Created 2026-06-21

Summary

Claim: "visibility improvements up to 37%" on the live engine Perplexity.ai (200-sample test).

Source: Aggarwal et al., arXiv:2311.09735 — Jun 28, 2024.

Confidence: Verified for the test result; caveat: sample of 200 on a single engine.

Why this matters for Candid: The only live-engine validation in the paper. Modest sample, but it crosses the gap from "works in the synthetic benchmark" to "works on a shipping AI answer engine."

Related entries

Depends on

reference Aggarwal et al., "GEO: Generative Engine Optimization" (Princeton / Georgia Tech / Allen AI / IIT Delhi, KDD '24) — citations + quotations + statistics in visible text lift source visibility by >40% across queries

Referenced by (2)

reference Research brief: the website as a working surface of the business — four capabilities, AI-citation decoupling, freshness as a real signal (June 2026) · relates-to
rule R3 — Favor body-text citations, quotations and statistics over schema markup as the AI-visibility lever; the peer-reviewed lift is in body text · depends-on