Privacy and limits

Privacy: Runs in your browser; files are processed on your device and not uploaded by the app; the page is downloaded from GitHub Pages and the CDN, which see your IP address; synthetic data only; not a validated or Part 11 system.

Limits: On held-out synthetic text this stand-in left 108 of 308 identifiers readable (the real model path: 91 of 308); every output needs human review. How this was measured.

Starting Python in your browser; first visit downloads about 30 MB.

Loading the page code.

De-identification review assist results: a table of flagged spans such as invented phone numbers, names, a ZIP code and initials, each with its entity type, offsets, redaction probability and action, above the sanitized domain rows.
Screenshot of this app's results on the bundled synthetic data. To use your own files, run it locally.