Human In The Loop
Every CitationLab post tagged human in the loop. This topic runs through several posts across the blog — case files where it caused a real problem, and guides for handling it in your own reference list.
Can AI invent fake references? Ours can't — by construction
The operation that produces fabricated references — generate a plausible source — is not implemented. What the model is actually asked, where references come from instead, and the one guard we removed on purpose.
How we find the newer version: seven engines, one verdict
Crossref, PubMed, Semantic Scholar, OpenAlex and the scraped tiers, asked in a fixed order. Why free-first is a metadata-quality rule, and what the engine ledger reveals.
We read your extracts, not your thesis
What actually reaches an AI provider during a citation check: the citation string, the parsed authors and year, and a capped window of surrounding words. Every citation goes; no chapter does.
Why every correction needs your click
Why CitationLab never applies an AI-formed correction on its own: the click is what turns a machine suggestion into a decision you can account for.