Tag

Deterministic Checking

Every CitationLab post tagged deterministic checking. 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.

Case Files

'Nelson SD, W.' — anatomy of a mangled author

Vancouver author lists read under APA grammar produce names no human has. How 'Nelson SD, Wong PT' becomes 'Nelson SD, W.', why a wrong parse is worse than no parse, and when a checker should refuse to guess.

Read the post →
AI & Integrity

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.

Read the post →
AI & Integrity

ChatGPT gave you citations that don't exist. Now what?

AI-invented references look perfect and cite nothing. The five tells that expose a hallucinated citation, how to verify one in under two minutes, and what to do with the claim it was propping up.

Read the post →
AI & Integrity

Deterministic first, AI second — and why the order is the whole design

Why CitationLab settles what it can with rules before any model is consulted, and what that ordering buys you in a reference check you can actually verify.

Read the post →
Case Files

From 1 thesis to 5,000: how we test

Every change we ship faces a jury of real theses — currently 105, being collated toward 1,000, headed for 5,000. The corpus method, the defects it surfaced, and the two times it caught our own mistakes.

Read the post →
AI & Integrity

It missed 27 citations, then told me it had found the last one

A general-purpose assistant missed 27 citations in one thesis chapter and said each time that it had found the last. That failure is why CitationLab runs rules before models.

Read the post →
AI & Integrity

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.

Read the post →