Automated README summary
Automatically summarized from the README on 25 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
judgevet is a typed Python client for TypeSafe's Jev (System One) judgment model, with CLI and optional MCP entry points. It lets applications ask structured questions about content, such as whether a support ticket concerns billing, and inspect the model's answers against a local acceptance policy.
How it uses Jev
The state is your content; a question describes what to evaluate. Jev returns typed answers: Noul gives probability of yes, Choice gives a selected label with per-label probabilities and confidence, Score gives a continuous score with rubric legend and per-level probabilities. Your code inspects these values or compares them with a local policy threshold.
Primitives:choicescorenoul
Technique worth stealing
Use typed questions (Noul, Choice, Score) to get calibrated probabilities, then apply a local acceptance policy threshold.
Try it
pip install 'judgevet==0.23.0', set JEV_API__KEY, then call HTTPSystemOneAdapter.system_one with state and questions.
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 material0.94
- Shows a System One patternnot found in the excerpt0.07
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.22 / 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 25 Oct 2026.