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
JevSpan is a Python library for zero-shot named entity recognition. Users define entity types in plain words and get entities with character offsets, calibrated probabilities, and decision traces, without training data or a GPU.
How it uses Jev
JevSpan splits text at punctuation and asks Jev a Choice over every candidate window per entity type. A second Choice verifies each nominee (the type, none, mixed, or partial), and a third settles its boundary. Jev's probabilities are returned as entity scores.
Primitives:choice
Technique worth stealing
Use a second Choice to verify each nominated window and a third to settle boundaries, rather than trusting one extraction pass.
Try it
pip install jevspan; export TYPESAFE_API_KEY=your-key; jevspan "Tim Cook announced that Apple will open a new office in Austin, Texas."
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 material0.97
- Shows a System One patternFound in material0.88
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersFound in material0.96
- Is a runnable toolFound in material0.67
- Top-10 learning shortlist signalFound in material0.73
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.52 / 2
- About JevFound in material0.99
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.