Automated README summary
Automatically summarized from the README on 30 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A reproducible, $0 benchmark comparing TypeSafe AI's Jev against embedding cosine similarity, a cross-encoder, and a trained classifier for Banking77 intent routing, with triage rules for when to trust each answer.
How it uses Jev
Jev receives the message plus the same 77 category descriptions as one Choice question and picks a category, returning a confidence. The saved predictions are replayed by `triage` to test confidence gates and cascades that send only uncertain messages to Jev.
Primitives:choice
Technique worth stealing
Compare a typed-choice model against local baselines on the same descriptions, then use its confidence as a gate to route only uncertain messages to it.
Try it
`python -m app.main run-cosine`, `run-trained`, `run-jev`, then `report` and `triage`; saved Jev answers need no key.
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 material0.82
- Shows a System One patternnot found in the excerpt0.05
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.82
- Is a runnable toolnot found in the excerpt0.09
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.56 / 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 30 Oct 2026.