What it is
Paper Radar scores every new arXiv and bioRxiv paper against plain-English interests using Jev, then publishes the top picks as a daily web page and RSS feed. It is for researchers who want to read only the few papers that matter.
How it uses Jev
For each paper, Jev answers one Noul per interest and exclusion, plus a Choice for paper type and a Noul for code release. The code combines probabilities via max or noisy-OR, applies thresholds and exclusions, and uses the result to build the daily page, RSS feed, and optional digests.
Primitives:choicenoul
Technique worth stealing
Atomic questions composed in code: one Noul per interest, speculative fan-out in a single call, then max or noisy-OR.
Try it
pip install git+https://github.com/Eliot5566/JEV-Paper-Radar && paper-radar demo
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.94
- Shows a System One patternyes0.62
- Handles uncertaintyno0.08
- Measuredyes0.91
- Runnableyes0.85
- Worth recommendingunclear0.45
- Model replicano0.32
- Problem scopescore on a 0–2 scale1.03
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.