Automated README summary
Automatically summarized from the README on 28 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An MIT-licensed local medical decision service that reproduces Jev's decision loop using two frozen open-weight readers, a fit-free confidence gate, and split-conformal candidate sets, evaluated on national medical licensing exams.
How it uses Jev
Jev is not used as a hosted model; instead, the project reproduces Jev-class judgment by combining two frozen readers' yes/no probabilities into a confidence, applying a Chow's rule gate for auto-release, and generating a split-conformal candidate set. The result is used in code to make per-item decisions.
Primitives:choicescore
Technique worth stealing
Fit-free router turns reader agreement into calibrated confidence and guaranteed candidate sets.
Try it
Run scripts/quickstart.sh after setup and model download; or use evaluate --mode fast|general|high.
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 material0.87
- Shows a System One patternFound in material0.91
- Describes handling uncertaintynot found in the excerpt0.29
- Reports measured numbersFound in material0.96
- Is a runnable toolFound in material0.66
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelFound in material0.96
- Solves a common problem (0–2)score on a 0–2 scale0.96 / 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 28 Sept 2026.