Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An open, local implementation of the System One / Jev idea: ask a small model a question and get a typed answer with a probability you can check, not a paragraph. For developers who want honest, testable decisions.
How it uses Jev
Jev is the closed, hosted model this project is an open take on. assay uses the same three question types (Choice, Score, Noul) and reads the model's odds for each option in one step, returning a choice, score, or yes/no probability with confidence, stability, and abstain flags.
Primitives:choicescorenoul
Technique worth stealing
Order-proofing by rotating option orders and averaging, plus a temperature calibrator that rescales odds and flags uncertain answers.
Try it
ollama pull gemma3; python -m assay decide --backend ollama --model gemma3 --state ... --question ...
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 material0.84
- Shows a System One patternFound in material0.62
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.28
- Is a runnable toolFound in material0.80
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelFound in material0.92
- Solves a common problem (0–2)score on a 0–2 scale1.33 / 2
- About JevFound in material0.94
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 13 Oct 2026.