Loading Epstein Files...

Preparing data

DOJ Epstein Files (File Transparency Act)

Independent AI triage of the DOJ File Transparency Act Epstein release, ranking the newest public records by investigative value.

Help keep this tool online. If this project helps your reporting or research, please support hosting and development so we can keep the lights on and continue processing the remaining DOJ volumes.

Donate to keep the lights on
Complete: All 0 of 0 documents have been processed and indexed.

Filtering

Adjust filters, then click Apply to run the query.

Indexed Progress

0 of 0

Rows Loaded

0

Avg. Importance

0.0

Top Lead Type

—

Last Updated

—

Top Power Mentions

Lead Type Breakdown

Top Agencies

Importance Score Distribution

How the Importance Score Works

Scoring uses an investigative triage prompt. Inputs can be OCR text or rendered page images, and outputs follow a strict JSON schema consumed by this viewer.

  • Evidence discipline: Explicit evidence only, with no invented names, dates, agencies, locations, or relationships.
  • Low-signal handling: Unreadable, decorative, duplicate, or weak-content pages are assigned low scores.
  • Lead focus: Scores prioritize actionable investigative value.
  • Entity normalization: Power mentions are canonicalized and controlled vocabularies are used.
  • Output contract: Each record includes headline, score, reason, insights, tags, power mentions, agencies, and lead types.

The rubric is integer-based from 0 to 100. Practical interpretation: 0-20 low signal, 21-50 limited to moderate leads, 51-70 strong leads, 71-85 high-impact leads, and 86-100 blockbuster leads.

Source & Credits

Primary source documents are from the U.S. Department of Justice Epstein files release under the File Transparency Act: justice.gov/epstein/files. Raw PDF corpus reference: yung-megafone/Epstein-Files. This project adds AI ranking and investigation-oriented indexing on top of those public records.