Tag

Extraction

Every CitationLab post tagged extraction. 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.

Inside CitationLab

Nothing gets lost: the conservation ledger

A citation checker you can trust must account for every line it read: kept, matched, or set aside — never silently dropped. How CitationLab's conservation ledger works.

Read the post →
Case Files

One author, two spellings, zero matches

A surname spelled two ways — a hyphen, a diacritic, a caps style — can make a citation checker report a missing reference and an orphan that are the same person. How name matching should actually work.

Read the post →
Case Files

The checker said 90% of my citations failed. The checker was wrong.

A doctoral thesis was told 90% of its citations were missing. The real defect was one broken assumption — and the true error count was two. How to read a failure report before you panic.

Read the post →
Inside CitationLab

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.

Read the post →
Case Files

When a university becomes an author

A reference whose 'author' is a department: how affiliations leak into the author slot, why blanket rules break real corporate authors like WHO, and how registry evidence repairs the entry — with your approval.

Read the post →