Jev in production › Document and record classification

JEV Paper Radar

Daily GitHub Action asks Jev one Noul per reader interest and exclusion plus a paper-type Choice for each new arXiv paper, and code builds must-read and maybe lists; screening mode recalled 96.9% of Cochrane reviewers' included studies (author).

Open on GitHub ↗

96.9%measured, as published by the source
Use
Document and record classification
Industry
Education and research
Form
Open-source tool
Stage
In production
Plugs into
GitHub Actions
Listed
2026-09-24
Found via
discord
Repository
Eliot5566/JEV-Paper-Radar
Stars
30
Forks
11
Last push
2026-10-09
Language
Python
License
MIT
JEV Paper Radar screenshot
docs/demo.png in the Eliot5566/JEV-Paper-Radar README, MIT; shown from GitHub.

The README opens with

Jev reads every new paper on arXiv each morning. You read the few that matter.

Plain-English interests · calibrated probabilities · about 6 cents a day for all of arXiv · fork and go, no server

A real run: 50 new arXiv papers judged by Jev in 5 seconds for $0.002. No key? paper-radar demo shows the same page offline.

arXiv now receives more than 30,000 papers a month (32,040 in June 2026), about 1,500 per weekday announcement. Nobody reads the listing any more. Keyword alerts miss papers that use different words, embedding recommenders quietly drop whatever does not look like your past reading, and running a chat LLM over the whole firehose every day is slow and costs real money.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for document and record classification