Text & documents
Numbers & maths
Data & formats
Security
Development & DevOps
Artificial Intelligence
Finance
Health & Wellness
Productivity
Games & Entertainment
Multimedia & design
Business
How to use
Your manuscript does not leave this page

Everything is computed in your browser: nothing is uploaded to any server. This matters because publishers (Elsevier, Springer Nature, Sage, Taylor & Francis, Wiley) and the NIH forbid reviewers and editors from uploading a manuscript to third-party tools. With an unpublished text, or one under review, this is the difference between being able to use a tool and not.

This does not say anything is wrong

It says that one number does not match another, and shows you the arithmetic so you can judge for yourself. A mistyped figure, a miscopied N and a number rounded twice all produce the same signal. Never use this screen as an accusation: use it as a list of things to check.

What this tool does NOT see

Results inside tables, incomplete test statistics (no degrees of freedom or no p), notation outside APA (square brackets instead of parentheses), formulas as images, and p-values corrected for multiplicity, which are flagged "uncheckable" on purpose. A clean screen does not mean the manuscript is clean.

Manuscript auditorWhich numbers in your paper or thesis don't add up
Manuscript auditorWhich numbers in your text don't add up — without it leaving your browser

Nothing you paste here is sent anywhere: it is all computed in your browser. That is why you can use it on an unpublished manuscript, or on one you are reviewing.

You are reviewingYou are about to submit a paper, or you are reviewing one for a journal.

The PDF is read in your browser: it is not uploaded anywhere. What comes out is the text, not the tables nor formulas that are images.

Decides what counts as "changes the decision": it is the threshold against which the reported and the recomputed value are compared.

What this screen has NOT looked at

  • Results inside tables: pasting as plain text loses the structure, so there is no way to tell which number goes with which.
  • Incomplete tests: missing degrees of freedom, or missing p.
  • Notation outside APA: square brackets instead of parentheses, a semicolon instead of a comma.
  • Formulas and results inserted as an image.
  • p-values corrected for multiplicity or sphericity: they are flagged "uncheckable" on purpose, because they need not follow from the test statistic.
  • Intervals with an open endpoint (95 % CI 73 to not reached), which are the norm in survival studies: there is no number to measure.

A clean screen does not mean the manuscript is clean.

On an in-house corpus of 19 hand-labelled test results, this recogniser finds 100 %, gets the verdict right on 100 % of those it finds, and its precision is 100 %. It is a regression net, not a measure of real-world accuracy: the corpus was written by whoever built the tool, so it only contains the cases they thought of. And against 151 test results from 34 published articles (Europe PMC, CC-BY) reviewed by hand, it extracts exactly the ones it should and leaves alone the 15 candidates that are not its business. In those same articles it also finds 97 confidence intervals, of which it can judge 65 without accusing a single one: those it cannot judge say why.