Automated README summary
Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Decima gives LLM systems a local judge: pass a situation, a question and your options, and get calibrated probabilities in milliseconds on one CPU core, with nothing leaving the machine. It also ships prompt-injection, leak and PII checks in English, Arabic and Persian.
How it uses Jev
Decima speaks TypeSafe's /v1/systemone format (choice, noul, score), so code written for Jev works after a one-line change. The Python Router.predict takes a state dict plus typed questions and returns per-question answers with calibrated probabilities; a local server accepts the official typesafe-sdk unchanged.
Primitives:choicenoulscore
Technique worth stealing
Options are scored independently, so shuffling them never changes the answer (0% order sensitivity in their tests).
Try it
pip install decima-ai, then run the decima CLI with --preset triage, or try the browser playground.
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 material0.70
- Shows a System One patternnot found in the excerpt0.24
- Describes handling uncertaintynot found in the excerpt0.02
- Reports measured numbersFound in material0.99
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.05
- Is a replica of the modelFound in material0.97
- Solves a common problem (0–2)score on a 0–2 scale1.83 / 2
- About JevFound in material0.70
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 Nov 2026.