Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An eval that runs spaCy textcat, TypeSafe Jev, Laya and Claude on the same email tasks (Enron spam, Bitext support routing, Swedish MASSIVE scenarios) with identical test rows and deterministic scorers, logged to Braintrust.
How it uses Jev
Jev is asked typed questions zero-shot about each email's state; its per-option probabilities and confidence are recorded as per-row metadata and scored against gold labels. Low-confidence answers are framed as a review policy. The README does not show the exact question-building code.
Primitives:choicescorenoul
Technique worth stealing
Tune category descriptions on the dev split only, then score the test set once.
Try it
uv sync; uv run python data.py; export TYPESAFE_API_KEY=...; uv run python eval_email.py
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 excerpt0.09
- Shows a System One patternnot found in the excerpt0.13
- Describes handling uncertaintynot found in the excerpt0.02
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolnot found in the excerpt0.08
- Top-10 learning shortlist signalnot found in the excerpt0.15
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.74 / 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 22 Oct 2026.