Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A benchmark for one narrow job: given a sentence that makes a claim and the passage it cites, decide whether the passage supports the sentence as written. It compares Jev against GPT-5.4, Claude Sonnet 5 and Gemini 3.1 Pro.
How it uses Jev
Jev is given the claim sentence and the cited passage as state, and returns a typed answer (support/not support) with a probability. The benchmark scores these answers against human labels and uses the probability for risk-coverage analysis.
Primitives:choicescore
Technique worth stealing
Using a typed answer with probability instead of free text, and sweeping confidence thresholds for risk-coverage.
Try it
Run `python3 mcnemar.py` or `risk_coverage.py --sweep-own`; see `results/` for raw outputs.
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 projectnot found in the excerpt0.39
- Shows a System One patternnot found in the excerpt0.11
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.98
- Is a runnable toolnot found in the excerpt0.05
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale1.21 / 2
- About JevFound in material0.98
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 25 Sept 2026.