Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Paper Radar is a serverless GitHub Actions pipeline that screens every new arXiv, bioRxiv, medRxiv or PubMed paper against plain-English research interests and publishes the top picks as a daily web page and RSS feed for researchers.
How it uses Jev
For each paper, one call sends a Noul per interest plus an exclusion Noul, a Choice for paper type, and a Noul for code release. The returned probabilities are combined in code (max of weight×p, or noisy-OR) with user-set thresholds to produce must-read, maybe and near-miss bands.
Primitives:noulchoice
Technique worth stealing
Atomic questions composed in code: one Noul per interest, all fanned out in a single call, then thresholds tuned and verified with calibrate.
Try it
pip install git+https://github.com/Eliot5566/JEV-Paper-Radar; paper-radar demo (no key), or paper-radar run --limit 50 with a key.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.97
- Shows a System One patternunclear0.51
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.91
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 23 Oct 2026.