Automated README summary
Automatically summarized from the README on 27 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python tool that turns a policy PDF (compliance manual, employee handbook) into fine-tuning datasets for System One / Jev-style decision models, with shared states, typed questions, rule-derived gold answers, and teacher probability distributions.
How it uses Jev
Jev's three primitives are the dataset's question types. A state_model generates scenario states; a teacher_model supplies probabilistic predictions averaged over --ensemble-n samples; gold answers are derived deterministically by rules in gold_rules.py (no LLM). Output is field-aligned to the training schema (state, qs, y, soft).
Primitives:choicenoulscore
Technique worth stealing
Deterministic rule-derived gold labels paired with teacher soft probability distributions, emitted as JSONL for direct fine-tuning.
Try it
python generate_config.py --pdf <file>.pdf --domain compliance, then python generate_dataset.py --pdf <file>.pdf --domain compliance --target 50 --output dataset_50.json
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 material0.95
- Shows a System One patternunclear0.53
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolunclear0.56
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelFound in material0.77
- Solves a common problem (0–2)score on a 0–2 scale1.02 / 2
- About JevFound in material0.97
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 27 Oct 2026.