Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
LitJev reproduces Jev's decision layer on off-the-shelf Hugging Face Qwen checkpoints. Define questions and options, load a Qwen model, and get typed choices with probability distributions from one API call, with no training and no generated answer text.
How it uses Jev
Each request's shared state opens every prompt; each question lists its options as plain text ending with 'Answer:', then each option's words are teacher-forced and their summed log-probability becomes that option's score. A softmax over scores yields the answer distribution, and typed JSON is built in code.
Primitives:choicescorenoul
Technique worth stealing
Score an option's own words rather than a letter code, so no label token prior pulls answers toward positions.
Try it
uv run --locked litjev --model Qwen/Qwen3.8-27B, then open http://127.0.0.1:8000/
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 material0.96
- Shows a System One patternnot found in the excerpt0.22
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.82
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelFound in material0.96
- Solves a common problem (0–2)score on a 0–2 scale0.87 / 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 1 Oct 2026.