The 16% Synthetic-Source Finding Depends on an AI Detector
A 712-query audit found detector-classified synthetic pages among citations, but 27.1% of cited URLs were not analyzed and page accuracy was not tested.
Tagged collection
Latest articles tagged “AI Citations”
Open an article for the complete method, evidence, limitations, and a focused reader discussion.
-
-
Most AI Citation Sources Appeared Once in a 16,069-Citation Sample
A source-long-tail recomputation plus a separate LinkedIn engine-mix example show why aggregate AI citation rankings can hide most domains and platform dependence.
-
You.com Answer API: Audit Citations, Excerpts, and Uncited Claims
Audit You.com Answer API citations, excerpts, live-source support and uncited claims with a 28-field downloadable claim-source ledger.
-
GPT-6 Astra’s BrowseComp Score Is Not a Citation Quality Score
OpenAI reports a 91.5% BrowseComp score for GPT-6 Astra. A new Perplexity customer story adds engineering context, not a consumer citation benchmark.
-
What 7,473 AI Citations Can and Cannot Tell Us
BrandGhost’s latest Observatory run offers useful signals about citation age and engine overlap, but its date and source-category coverage materially limit broader claims.
-
ChatGPT Library Citations Are Not Public Web Visibility
ChatGPT Library can cite private or workspace-shared files. Use the ownership, permissions and signed-out tests to separate connected-source provenance from public web visibility.
-
ChatGPT Financial Services Adds an Experian Credit Layer
ChatGPT can now combine authorized Experian credit data with hosted premium datasets, entitled connections, private files and the public web. Provenance determines what the answer means.
-
Perplexity Premium Data Sources: Included and Licensed Access
Perplexity now documents included premium sources and licensed connectors. This access matrix separates plan eligibility, partner entitlements and citation inspection.
-
Perplexity Citation Audit: When a Link Does Not Support the Number
We recalculated two public Perplexity citation files, separated row and claim denominators, and built a four-state audit for numerical source support.
