Automated README summary
Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Jupyter notebook comparing TypeSafe's Jev decision model with GPT-6 Luna on the CLINC150 intent-classification benchmark, including out-of-scope inputs with and without an `other` option.
How it uses Jev
Jev is used on OpenRouter to make intent decisions over CLINC150 items, with per-intent one-line descriptions as prompts. The notebook measures consistency, cost, and behavior on out-of-scope input; results are compared head-to-head with GPT-6 Luna.
Primitives:choice
Technique worth stealing
Using a decision model with an explicit `other` option to handle out-of-scope input.
Try it
cp .env.example .env, add OpenRouter key, uv sync, uv run jupyter lab jev_clinc150.ipynb
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 material0.61
- Shows a System One patternunclear0.49
- Describes handling uncertaintynot found in the excerpt0.23
- Reports measured numbersnot found in the excerpt0.19
- Is a runnable toolnot found in the excerpt0.07
- Top-10 learning shortlist signalunclear0.57
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale0.94 / 2
- About JevFound in material0.97
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 11 Oct 2026.