Automated README summary
Automatically summarized from the README on 10 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A bakeoff repo testing whether a cheap prefilter plus a thin rewrite skill can replace loading a large writing skill on every draft, aimed at teams maintaining an agreed copy quality bar at low cost.
How it uses Jev
Jev is placed on a hook as a cheap typed classifier so a second full draft is not generated every time. The README describes the hook as the right shape (cheapest decision, typed output, no generated prose) but does not specify which Jev primitives are used or the exact state passed.
Technique worth stealing
Deterministic heuristics first, then a calibrated classifier for residual patterns; rewrite only on a failed gate.
Try it
python3 evals/heuristics.py evals/fixtures
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 projectnot found in the excerpt0.24
- Shows a System One patternnot found in the excerpt0.22
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolnot found in the excerpt0.30
- Top-10 learning shortlist signalnot found in the excerpt0.16
- Is a replica of the modelnot found in the excerpt0.23
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 2
- About JevFound in material0.95
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 10 Nov 2026.