nqzaiBlogTag archive
An orphan page is a live page with zero internal links pointing to it — invisible to crawl-based discovery and doubly invisible to the low-timeout AI crawlers that never render JavaScript or follow deep site trees. Here's a real audit process for finding them, backed by named studies, not fabricated stats.
AI retrieval systems don't crawl a site the way a PageRank algorithm does — they chunk pages, embed passages, and lean on anchor text as disambiguating context. Here's what the research actually supports about internal link structure and AI citation, and what it doesn't.
Retrieval-augmented generation systems don't rank pages, they retrieve passages — which changes what "topic cluster architecture" needs to do. Here's what the research on chunking, query fan-out, and citation behavior actually says.
