Model-recalled citation

A model-recalled citation is a source name, URL, or publication that a language model mentions or attributes a claim to based on patterns learned during training, rather than a page it actually retrieved and read while answering. It looks identical to a citation from live retrieval in the output text, but nothing was fetched in that session - the model is recalling, not reading.

Tools that query a model directly through an API, without a browsing or search step attached, can only observe what the model says, not what it retrieved, because nothing was retrieved. Any source names in that output are model-recalled: plausible, sometimes accurate, but drawn from training-data patterns rather than a verified fetch of the current page.

This is a real measurement limitation, and ClerAEO AI reports it openly rather than blurring the line: API-only queries surface model-recalled citations, while browsing-enabled or search-integrated modes reflect observed retrieval. The two are not interchangeable evidence of visibility, and any AEO tool that treats them as identical is overstating what it actually measured.