Skip to main content
Manusights · Free Tool

Verify

Citation Claim Checker

Paste a sentence with a citation. We check whether the paper actually says what you think it says.

We don’t train AI on your data. Citations use short-lived result caching.

1

Paste your claim

A sentence from your manuscript that cites a paper (author-year or numbered)

2

We find the paper

Searched across 200M+ papers in seconds

3

Get a verdict

Supported, Partially Supported, or Not Supported

0/3 checks used today

Why citation accuracy matters

Studies show 25-54% of citations in published papers contain errors, and 80% of authors admit they haven't read the full text of every paper they cite. Citation misrepresentation -- where authors claim a paper showed something it didn't -- is one of the most common issues reviewers catch.

This tool checks whether the paper you're citing actually supports the specific claim you're making. It goes beyond checking if a DOI resolves -- it reads the abstract and compares it to your statement.

Limitations

  • - Verification is based on the paper's abstract only. Specific sub-analyses or supplementary findings may not be captured.
  • - Numbered references like [1] require the full reference entry from your bibliography (paste it in the reference field).
  • - Papers not indexed in Semantic Scholar, CrossRef, or PubMed may not be found.

Calibrated from early work with 35+ CNS-experienced reviewers and senior scientists. Their reviewer language shaped how Manusights flags unsupported claims, weak evidence, journal-fit risk, and likely reviewer objections. Logos indicate researcher affiliation, publication context, or calibration-network context, not endorsement.

Harvard
MIT
Stanford
Oxford
Nature
Science
Cell
The Lancet

See exactly how these tools score and what they don’t do →

Check your entire manuscript

Citation-risk checks, methodology assessment, journal fit analysis, and a prioritized fix list. Delivered in about 30 minutes.

Verify every citation in my manuscript — $39

Free preview first. Pay only if the full report is useful.

We don’t train AI on your data. Inputs use short-lived result caching.

Want the data sources behind every verdict? Read the full methodology · Semantic Scholar / CrossRef / PubMed corpus, refusal cases, and known limitations.

Checking whether references are retracted, not just miscited? Run Manusights Sentry · paste a bibliography, get per-reference flags for retractions, expressions of concern, and hijacked-journal clones.

Already chose a target journal? Run Manusights Lens · returns a 0-100 scope-fit risk score for the venue you have already chosen, with named scope-fit patterns and lower-risk alternatives.