Automated README summary
Automatically summarized from the README on 21 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
poorjev is an open-source, local-first decision layer for LLM apps. It provides typed decisions (Choice, Score, Noul) with calibrated confidence, runs offline without an API key, and is aimed at developers needing private, fast structured decisions.
How it uses Jev
poorjev reproduces Jev's typed-decision interface on a local zero-shot NLI model. It takes a state and typed questions (Choice, Score, Noul), runs one batched pass, and returns calibrated probabilities. Calibration uses temperature scaling and conformal abstention. The result is used as schema-valid answers with confidence.
Primitives:choicescorenoul
Technique worth stealing
Temperature scaling with conformal abstention to calibrate confidence and enable abstention.
Try it
pip install "poorjev[local]" then use Client().ask() as in the README.
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 material0.88
- Shows a System One patternnot found in the excerpt0.38
- Describes handling uncertaintynot found in the excerpt0.14
- Reports measured numbersunclear0.59
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalnot found in the excerpt0.20
- Is a replica of the modelFound in material0.95
- Solves a common problem (0–2)score on a 0–2 scale1.62 / 2
- About JevFound in material0.91
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 21 Sept 2026.