Automated README summary
Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An open-source port of Jev's typed-decision format that replaces the LLM comparator inside two published search rerankers, BlitzRank's tournament graph and Reranker-Guided Search, for retrieval and RAG.
How it uses Jev
Each match is one Choice scored over k candidate paths in a single forward pass with zero decoded tokens. Both rerankers call the same decision model through JevPredictor.decide(), sharing one question encoding, ordering rule and accounting.
Primitives:choice
Technique worth stealing
One forward pass over k candidate paths scores a Choice, giving a calibrated distribution instead of a decoded permutation.
Try it
python scripts/example_rank.py --device cuda:0 prints one decision end to end.
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 projectFound in material0.96
- Shows a System One patternunclear0.42
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.98
- Is a runnable toolnot found in the excerpt0.35
- Top-10 learning shortlist signalFound in material0.68
- Is a replica of the modelFound in material0.96
- Solves a common problem (0–2)score on a 0–2 scale1.32 / 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 11 Oct 2026.