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
A benchmark harness that tests whether TypeSafe Jev's returned probabilities match human ground truth, comparing Jev, Claude Haiku/Sonnet and a TF-IDF logistic regression baseline across five public human-labeled datasets.
How it uses Jev
Each dataset item becomes a typed decision with a state, question and named choices. The jev arm sends each decision as a single choice question and reads Jev's native probabilities object; results feed calibration metrics, recalibration and cascade analysis.
Primitives:choice
Technique worth stealing
Score every arm with ECE, Brier, NLL and selective-prediction metrics against human labels, then test whether post-hoc temperature/Platt/isotonic scaling erases any native calibration advantage.
Try it
pip install -e ".[dev]"; jevlab fetch; jevlab run --dry-run; jevlab report
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 projectnot found in the excerpt0.35
- Shows a System One patternnot found in the excerpt0.08
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolnot found in the excerpt0.07
- Top-10 learning shortlist signalnot found in the excerpt0.08
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.20 / 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 1 Nov 2026.