Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Racket library that calls the TypeSafe System One API, letting Racket programs ask typed questions about a state blob and receive calibrated probabilities instead of generated text.
How it uses Jev
Jev evaluates batched typed questions against a state: noul returns a yes probability, choice returns a winner plus distribution, score returns a weighted value plus confidence, locate returns a box region in an image. Answers are read via typed accessors like noul-answer-value and choice-answer-value.
Primitives:choicescorenoul
Technique worth stealing
Batch all questions into one request so Jev reads the state once and evaluates every question against it.
Try it
raco pkg install --link /path/to/jevracket, then (require jev) and call make-client and ask.
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 material0.92
- Shows a System One patternnot found in the excerpt0.12
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.22 / 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 3 Nov 2026.