Research Foundation

Built on peer-reviewed science, not marketing claims.

GEO: Generative Engine Optimization

KDD 2024 — Princeton, Georgia Tech, AI2, IIT Delhi
Tested 9 optimization strategies across 10,000 queries on GEO-bench. Validated on real Perplexity.ai with 22-37% improvements.
Key: Citations increase AI visibility up to +115%. Statistics add +40%. Keyword stuffing has ~0% effect.
Cite Sources +27-115%
Quotations +41%
Statistics +33%
Fluency +29%
Technical Terms +18%
Authority +16%
Readability +14%
Unique Words +7%
Keyword Stuffing ~0%
Read paper →

AutoGEO: Automatic Generative Engine Optimization

ICLR 2026 — Carnegie Mellon University
Automatic rule extraction from generative engines via LLMs + reinforcement learning. +50.99% over Princeton baseline. Introduces GEU (utility) metric.
How we use it: Informs scoring weight updates. Answer-first structure and passage density checks are based on AutoGEO findings.
Read paper →

C-SEO Bench: Conversational SEO Methods

2025 — Puerto et al.
Most conversational SEO methods are ineffective and often negative. Gains decrease as adoption increases — zero-sum competitive dynamic.
How we use it: Validates our focus on infrastructure over content manipulation. We build white-hat GEO tools.
Read paper →

Schema Markup & AI Citations

Growth Marshal, Feb 2026 — 730 pages
Rich schema (5+ attributes): 61.7% citation rate. Generic schema: 41.6%. Generic actually underperforms no schema.
How we use it: Schema richness check differentiates rich vs generic. Generic gets zero bonus.

AI Citations Report 2026

OtterlyAI — 1M+ citations analyzed
73% of sites have technical barriers blocking AI crawlers. Reference-grade content gets 3-5x more citations.
How we use it: robots.txt, CDN, and JS rendering checks address the 73% barrier problem.

AI Mode Citation Factors

SE Ranking, 2025 — 2.3M pages
Flesch-Kincaid Grade 6-8 is the sweet spot. Sections of 100-150 words are optimal. FAQ schema has zero impact — only real FAQ content matters.
How we use it: Readability, passage density, FAQ-in-content, and section length checks.
GEO Optimizer focuses on infrastructure optimization (robots.txt, llms.txt, schema, meta, content structure) — not content manipulation. The adversarial research confirms that manipulative techniques degrade the ecosystem.