An adversarial AI referee for empirical economics: finds p-hacking, cherry-picking and specification search, then re-runs the result.
-
Updated
Oct 2, 2026 - Python
An adversarial AI referee for empirical economics: finds p-hacking, cherry-picking and specification search, then re-runs the result.
Critical statistical review of research papers: extract reported tests, recompute them, flag questionable analyses.
开源论文体检工具 PaperGuard:扫描论文 PDF 的统计自洽、数字一致与图片完整性疑点,帮助科研人员发现学术不端线索,MIT 开源。Paper screening for scientific integrity.
Check AI-written statistics with evidence. Re-runs analyses and notebooks, tests each statistical test's assumptions on the real data, recomputes reported p-values (statcheck-style) and lints analysis code. Posts the result on pull requests; an optional LLM agent proposes corrected analyses that are re-run to verify them. pip install stataudit
statcheck-ml in the browser: drop a PDF, check its statistics. Demo: https://rasoulnorouzi.github.io/rasoulnorouzi-statcheck-ml-web/
To associate your repository with the statcheck topic, visit your repo's landing page and select "manage topics."