Buried across hundreds of thousands of government-released pages — emails, legal filings, financial records — are scholarly papers spanning psychology, neuroscience, artificial intelligence, law, economics, and more.
JEEScholar indexes academic papers and books found within the DOJ's Jeffrey Epstein Files and the House Oversight Committee release. All documents are public federal records. We extract, identify, and catalog these papers and books so researchers and the public can find them.
Every document from the DOJ Epstein Files (Datasets 1–12) and the House Oversight release is downloaded and converted to searchable text.
Heuristic filters scan for academic signals — abstracts, DOIs, citations, affiliations — then an AI classifier confirms each candidate.
Each paper is matched against CrossRef, Semantic Scholar, and OpenAlex to retrieve its DOI, authors, journal, citation count, and abstract.
We extract the Epstein Files provenance: which dataset, Bates number, and any covering email metadata (sender, recipient, date).
All documents come directly from government releases. The original PDFs served here are the government-released scans — not republished versions. The detection pipeline is automated but every paper is manually verified before inclusion. Processing is ongoing as new datasets are released.
JEEScholar was built by Antonio Maculus. The entire pipeline — scraping, detection, enrichment, and this site — was built from scratch as an independent research project to make these public records accessible and searchable.