Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Classifies a business's description of operations into one of 1,012 NAICS 2022 industries, or holds it for a person. Built for insurance applications where a wrong neighbouring code misprices risk unnoticed.
How it uses Jev
Code builds a closed candidate list via Postgres full-text search, spelling correction, a lexicon, and a NAICS tree walk. Jev ranks that closed list, answering typed questions (pick one option; is this statement true) with probabilities. Measured gates then act or hold; Jev never invents or rejects codes.
Primitives:choicescore
Technique worth stealing
Code owns every action and gate; Jev only ranks a closed list of real industries, so it cannot invent a code or choose none-of-the-above.
Try it
Bring up the stack with Docker Desktop and git; clone the repo and run the setup script.
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 material0.90
- Shows a System One patternFound in material0.85
- Describes handling uncertaintyFound in material0.78
- Reports measured numbersFound in material0.85
- Is a runnable toolFound in material0.62
- Top-10 learning shortlist signalunclear0.59
- Is a replica of the modelFound in material0.63
- Solves a common problem (0–2)score on a 0–2 scale1.02 / 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 4 Nov 2026.