AI Citation Checker
A free reference checker for AI drafts. Paste the draft and it resolves every DOI, link and Author (Year), reads the source, and holds it against the sentence that cites it.
A citation fails three ways: the source does not exist, it exists but belongs to someone else, or it exists and does not say that. A DOI validator catches the first. This reference checker looks up each reference in Crossref, the registry that issues DOIs, or on the live page. Then a model reads the source and quotes the passage that supports or contradicts your sentence.
Best for newsletter writers, journalists and researchers who publish AI-assisted drafts with references.
Free: one check a day, no signup. Paid plans check every claim and citation across four AI models, from $20 a month.
Looking each one up in Crossref or on the live page, then reading the source.
Deep runs in three steps: four models answer, two critics review, and one mediator writes the final call. Leave this page open and the result lands here.
Citation Checker runs the moment you sign in, on the text you just pasted. Nothing to enter twice.
A saved check is kept for 24 hours.
Check something else
You've used up today's free runs on this check.
Come back tomorrow for another free run.
Why a DOI That Resolves Is Not Enough
A reference can point to a real paper and still be wrong, because the paper never makes the claim. To catch it, the check reads the paper next to your sentence.
Extract every reference
The check pulls every DOI, link and Author (Year) citation out of the text, along with the sentence that leans on it.
Resolve it for real
DOIs go to Crossref, links to the live page, an author-year reference to a search on author and year and then a match on title. A DOI nobody registered or a page that 404s counts as nonexistent. A real paper under the wrong name or year counts as misattributed. Neither verdict comes from a model.
Read the source against your sentence
For every source that resolves, the model reads the text and quotes the passage that supports or contradicts what you wrote. Supported needs a quote. No quote, no pass.
We built this for one error: a draft that cites a real paper for something the paper never says. A link checker cannot catch it, and it is the error that ends up in a correction.
This check reads the references. To check the claims between them as well, run the draft through the AI fact checker, which runs the claim check and this one together.
Checking an AI answer against policy pages you approved? See how to verify AI answers against your sources, with a real run on three GOV.UK pages.
Example Check
From a real Council run on 21 August 2026, edited for length. GPT, Claude, Gemini and Grok agreed on every reference.
"Three sources anchor this piece. Vaswani et al. (2017) introduced the Transformer, an architecture based solely on attention mechanisms (https://arxiv.org/abs/1706.03762). A 2023 Nature study found that 80% of coders use AI daily (https://doi.org/10.1038/s41586-023-99999-1). Ioannidis (2005) proved that 80% of medical studies are wrong (doi:10.1371/journal.pmed.0020124)."
Of the three references, one holds up and one does not exist. The third gets its source wrong: the draft says Ioannidis proved 80% of medical studies are wrong, but the paper argues that under some conditions most findings are more likely false than true.
Attention Is All You Need
SOURCE SAYS: “We propose a new simple network architecture, the Transformer, based solely on attention mechanisms…”
The source proposes the Transformer and describes it as based solely on attention mechanisms. The 2017 date matches the record.
Crossref has no record of this DOI, so nothing backs the figure in the draft.
Why Most Published Research Findings Are False
SOURCE SAYS: “It can be proven that most claimed research findings are false. Simulations show that for most study designs and settings, it is more likely for a research claim to be false than true.”
The paper says that under some conditions most findings are likely false. It gives no such figure and does not limit itself to medicine.
Frequently Asked Questions
It finds every reference in your text and looks each one up in Crossref or on the live page. Then a model reads the source and quotes the part that backs or contradicts your sentence. Each reference gets a verdict: supported, misrepresented, misattributed, nonexistent or unverifiable.
It includes one. A DOI validator tells you whether the identifier resolves. That catches an invented reference. It misses a real paper cited for something it does not say. This check resolves the DOI and then reads the paper.
Paste the reference. A DOI goes to Crossref, a link to the live page, an author and year to a search. A DOI nobody registered or a page that 404s comes back nonexistent. A real paper whose author or year does not match what you wrote comes back misattributed. The lookup decides both, not a model's opinion.
When the quote sits in a sentence that cites a source, yes. The model looks for the quoted words in the source text and reports misrepresented when they are not there or say something else. A quote with no source attached has nothing to be checked against; add the link.
The source exists, but we could not read its text from here, usually a paywall or a site that blocks automated fetches. We say so instead of guessing. Paste the relevant passage into the draft and the check can read that instead.
It resolves links and DOIs and reads any source page it can fetch, so a brief that links to its authorities works. The check does not resolve case citations in reporter format yet; those still need a legal database.
Yes. Paste the answer with links to the policy pages or documents it should draw from, and the check reads each one against the sentence that cites it. Private documents need a reachable URL; a paywalled or internal page comes back unverifiable.
A model asked to vouch for a reference tends to vouch for it. Here, a lookup in Crossref or on the live page decides whether a source exists and who wrote it. The reading step marks a reference supported only when the model can quote the passage. On a paid plan, four models from different labs read the same sources. Each reference gets their majority verdict, and you see every vote.
Every run produces a receipt that is private unless you share it; it holds the text you pasted and the result. We fetch sources straight from their publishers. Your content is never used for model training.
Powered by TrueStandard
Four independent models check every claim in your draft.