Automated README summary
Automatically summarized from the README on 26 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jsort orders lines, paragraphs, or whole files along a plain-English criterion. It shows Jev two texts at a time and asks which ranks higher, then fits a Bradley-Terry scale. Useful for ranking statements, tickets, or documents by a described quality.
How it uses Jev
Jev answers pairwise Choice questions: given two texts and a dimension like "more hawkish about inflation", which ranks higher? jsort asks a few pairs per text, fits a Bradley-Terry scale to the probabilities, and prints texts from top to bottom, optionally with scores and standard errors.
Primitives:choice
Technique worth stealing
Fit a Bradley-Terry scale to sparse pairwise Jev comparisons, yielding scores with standard errors rather than just an order.
Try it
uv tool install jev-sort; jsort -o "more hawkish about inflation" presser.txt
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.89
- Shows a System One patternnot found in the excerpt0.13
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.30
- Is a runnable toolFound in material0.81
- Top-10 learning shortlist signalnot found in the excerpt0.37
- Is a replica of the modelunclear0.40
- Solves a common problem (0–2)score on a 0–2 scale0.86 / 2
- About JevFound in material0.97
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 26 Sept 2026.