Loading your experience…
Whiteship Research Report
What makes AI models cite one source and ignore another?
A Whiteship research study based on 69,642 AI answers and 1.72 million visited source rows across OpenAI, Google, Anthropic, Grok, and Perplexity.
Correlation-driven, not speculativeMulti-provider sourcing patternsEnglish PDF ready to share internally
AI answers analyzed
69,642
Answer runs linked to evidence and provider metadata.
Visited source rows
1.72M
Observed web-search source rows across the full study sample.
Domain use rate
42.2%
Visited domains that end up cited in final answers.
Exact URL use rate
32.7%
Visited URLs that are cited as the exact final source.
What this Whiteship study shows
Citation behavior follows a recognizable source hierarchy.
This study covers 69,642 analyzed answer runs and 1.72 million visited source rows across five providers. Metrics are correlation-based and describe observable citation patterns, not hidden causal reasoning inside model ranking systems.
Read the condensed articleSite typology
Citation rate
Interpretation
Corporate / brand
53.5%
Highest citation conversion. Official pages outperform noisy intermediaries.
Commerce / product
49.8%
Transactional pages convert well when they carry clear product specificity.
Documentation / knowledge base
49.1%
Structured explanations and canonical references are frequently retained.
Editorial / article
42.5%
Strong when topical alignment is high, weaker when generic.
Comparison / aggregator
35.1%
Often visited, but less likely to survive into final citations.
Community / social
25.0%
Lowest conversion. Social chatter is explored, but rarely used as final evidence.
Qualitative patterns
The strongest source traits are visible before citation even happens.
01
Officiality wins
Brand-owned, documentation, and product pages outperform social and aggregator sources because they read as canonical, attributable, and easier to trust.
02
Lexical fit matters
Pages whose title and URL slug strongly match the originating query are more likely to convert from visited to cited.
03
Specific pages beat generic hubs
Deep pages with descriptive paths outperform flat category URLs when the model needs a precise fact or recommendation anchor.
04
Provider behavior differs
OpenAI runs in this Whiteship study retain visited sources much more aggressively than Anthropic, which suggests provider-specific sourcing policies or retrieval behavior.
Brief summary
What this research brief establishes.
This study maps the structural and qualitative patterns behind citation behavior: which pages get visited, which domains actually make it into final answers, and which source types convert from visited to cited most reliably.
01
Officiality wins
Brand-owned, documentation, and product pages outperform social and aggregator sources because they read as canonical, attributable, and easier to trust.
02
Lexical fit matters
Pages whose title and URL slug strongly match the originating query are more likely to convert from visited to cited.
03
Specific pages beat generic hubs
Deep pages with descriptive paths outperform flat category URLs when the model needs a precise fact or recommendation anchor.
Book a demo
Book a demo today with our team.
See the workflow live with our team and understand how Whiteship turns AI search visibility and source-citation signals into something your team can act on.