9.7% of citations that credit a specific finding badly misreport the paper they cite.
About 1 in 14 citations overall (7.2%). Background citations: 5.6%. Methods and tools: 4.8%.
Badly misreport the cited paper, by what the citation is used for
Not in the test's plan; the same order held in an earlier, separate set of 500 citations (7.8%, 5.4%, 3.6%).
Not in the test's plan. The same order held in an earlier, separate set of 500 citations.
Source: SaneCite citation-accuracy test (batch 6): 915 random citations from open-access PubMed Central papers, 2015–2025. Measured against AI readers, not people; pending human review. Data as of 22 Oct 2026.
Source: SaneCite citation-accuracy test (batch 6), 915 citations, 22 Oct 2026, pending human review · sanecite.com/charts
Show the numbers
| What the citation is used for | Judged | Badly misreport | Share (95% CI, %) | Any error |
|---|---|---|---|---|
| Credits a specific finding | 413 | 40 | 9.7% (7.2–12.9) | 117 (28.3%) |
| Background | 357 | 20 | 5.6% (3.7–8.5) | 50 (14.0%) |
| Method or tool | 124 | 6 | 4.8% (2.2–10.2) | 17 (13.7%) |
| All judged (incl. 21 data-source citations) | 915 | 66 | 7.2% (5.7–9.1%) | 186 (20.3%) |
1,000 random citation pairs from Open-access PubMed Central research and review articles, 2015-2025, citing an open-access paper with a PubMed ID; 915 could be judged. Answer key: two blind AI readers from different model families, disagreements settled by a third read. 95% intervals are Wilson intervals.
Free to share, with credit.
Download the image, paste the caption, or link to this page. Please credit SaneCite (sanecite.com). The numbers come from the open test result; nothing here is picked by hand.
- How it was read.Two AI readers from different model families read each citation next to the paper it cites, without seeing each other's answers; a third read settled disagreements.
- What "badly misreport" means.The cited paper does not say what the citation credits to it, says the opposite, or is about something else. Smaller errors, such as an overstated finding, are counted separately.
- What it covers.Random citations from open-access research and review papers in PubMed Central, 2015 to 2025, where the cited paper is also open access.
- Check it yourself.This chart's data · the full test result · how the test worked.