Citation check for AI output

Paste a document. You get back mechanical convictions — counts whose members are not named, listings that do not match contents, marker vocabulary that slipped, totals graded above their weakest part, and internal references that resolve to nothing. Locations included. No style advice, no rewriting.

Two of these read any document: counts of its own parts, and references that resolve to nothing. The other three read documents that carry a structured listing, a marker vocabulary, or a graded total — common in specifications and reports built to a standard, absent from ordinary prose. When a check does not apply, this tool says so rather than passing it silently.

It also reports whether the sources your document cites can actually be retrieved by an automated reader, and why not where not. That is not the same question as whether a claim is true, and the report says so.

Free: 3 checks per day, and 3 documents per day for the source retrieval, counted separately. Up to 200 KB per document. Your document is checked and discarded — never stored. We keep one anonymous daily count of how many documents convicted, and nothing else. These checks are pure parsing: no AI model reads your text on this page.


The example is our own document, built to fail two of the checks — a count whose members do not match, and a reference that resolves to nothing. It is a demonstration, not a typical result.

Weakest Mark · a verdict service for machine-made claims. Need more than three a day? A prepaid pack of the same mechanical checks is on the pricing page. Packs also run the grounding pass — we fetch the source your document cites and compare the claim against what it actually says. It is under development and we say so; there is a real recorded run on that page so you can judge it before paying.
We ran these checks on a handbook of our own and published everything they raised — including the one finding we got wrong and had to retract.
Impressum · Datenschutz / Privacy