Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A research prototype that turns plain-language requests into native Text-Fabric search queries for a loaded corpus, aimed at researchers querying Text-Fabric corpora without writing TF syntax by hand.
How it uses Jev
Jev is an optional bounded-decision adapter: it answers typed Choice/Score/Noul questions over corpus-schema-derived candidates to build a typed query IR, which a deterministic compiler then renders into native TF search text. Measured evaluations report low success and frequent abstention; it is not a recommended default parser.
Primitives:choicescorenoul
Technique worth stealing
Constrain the model to bounded structured decisions over schema-derived candidates, then compile deterministically so unsupported or ambiguous requests abstain.
Try it
python -m pip install -e '.[dev,jev]' then run python -m pytest -q
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 projectFound in material0.92
- Shows a System One patternunclear0.51
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.80
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale0.79 / 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 Oct 2026.