Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-judge is a Python CLI and SDK that evaluates already-recorded LLM inputs, context, and outputs against declarative YAML/JSON assertions, producing terminal, JSON, JUnit, Markdown, GitHub annotation, and HTML reports for local development and CI.
How it uses Jev
Each assertion maps to a Jev decision: faithfulness, hallucination, and safety use Noul; relevance uses Score; Choice handles option selection. The runner sends supplied input, context, and output to a live TypeSafe client or the local mock, then records pass/fail and probability per decision.
Primitives:noulscorechoice
Technique worth stealing
Declarative YAML assertions mapped to typed Jev decisions, with an offline mock for trying the workflow without inference calls.
Try it
pip install jev-judge, then run jev-judge init and jev-judge test evals/ --mock.
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 patternunclear0.48
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersunclear0.55
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalunclear0.46
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.40 / 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 28 Oct 2026.