Automated README summary
Automatically summarized from the README on 10 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-eval measures and calibrates TypeSafe AI's Jev on your own labeled data. It reports per-question accuracy, calibration (ECE, reliability table), risk-coverage, and recommends confidence cut-points for gating workflows.
How it uses Jev
Jev answers labeled questions (Choice, Noul, Score) on each row's state. jev-eval compares answers to gold labels, computes accuracy and calibration, then recommends confidence cut-points for auto-deciding confident cases and escalating the rest.
Primitives:choicescorenoul
Technique worth stealing
Bootstrap with out-of-bag scoring to honestly estimate gate accuracy and avoid optimistic same-rows bias.
Try it
export JEV_API_KEY=...; jev-eval run --data labeled.jsonl --config jev-eval.json --cache run.jsonl
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 material0.86
- Shows a System One patternFound in material0.85
- Describes handling uncertaintyFound in material0.84
- Reports measured numbersnot found in the excerpt0.13
- Is a runnable toolunclear0.40
- Top-10 learning shortlist signalunclear0.58
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 2
- About JevFound in material0.98
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 10 Oct 2026.