Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jevextract is a Python library for grounded information extraction from text using a YAML schema. It returns mentions with exact character offsets, confidence scores, and closed-set attributes, avoiding hallucination by construction.
How it uses Jev
Jev answers one Choice per candidate span (which class or none) and one Noul per sentence-level class. Decisions are thresholded, overlaps resolved, and close calls flagged for review. Attributes are extracted with an additional call.
Primitives:choicenoul
Technique worth stealing
Code proposes candidate spans with exact offsets; Jev only chooses classes, ensuring every extraction is a substring.
Try it
pip install git+https://github.com/gabazureus/jevextract, set TYPESAFE_API_KEY, run jevextract doctor.
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 material0.95
- Shows a System One patternFound in material0.84
- Describes handling uncertaintyFound in material0.80
- Reports measured numbersFound in material0.96
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalunclear0.59
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.53 / 2
- About JevFound in material0.98
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 25 Sept 2026.