Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A research project that reverse-engineers, replicates, and extends TypeSafe AI's Jev, the first commercially deployed decision model, for researchers studying calibrated probabilistic decision systems.
How it uses Jev
The README does not describe how Jev is invoked in code; it only states that probing/ performs black-box API probing of Jev (21 probes, 5,620 API calls, 5 preregistered controlled experiments) and that the replication model is compared against Jev's benchmark scores.
Primitives:choicescorenoul
Technique worth stealing
Reranker pretraining transfers to decision scoring: a 150M cross-encoder with trained decision heads beats a vanilla encoder at equal params.
Try it
git clone https://github.com/Oaklight/krino.git; cd krino; pip install -e '.[data]'; python -m data.pipeline banking77 sst2
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 material0.90
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolnot found in the excerpt0.21
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelFound in material0.82
- Solves a common problem (0–2)score on a 0–2 scale1.09 / 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 4 Nov 2026.