Automated README summary
Automatically summarized from the README on 4 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
This repository holds test sets, code, raw judge outputs and analysis for an experiment comparing three automatic translation-quality judges on Latin→English translation, targeting fluent misglosses.
How it uses Jev
JEV (jev-1.13.0) is tested as an automatic judge with its original 3-question set and a 24-question set decomposed along the MQM error taxonomy. It returns typed, probability-valued answers to structured questions; outputs are scored and compared to MQM issue lists.
Primitives:choicescorenoul
Technique worth stealing
Decomposing JEV's questions along MQM categories did not improve discrimination but lets JEV return typed errors.
Try it
Run from repo root: python 08_working_scratch/pipeline_scripts/jev_judge.py --input ... --output ...
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 excerpt0.11
- Shows a System One patternunclear0.50
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.13
- Is a runnable toolnot found in the excerpt0.06
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale0.94 / 2
- About JevFound in material0.97
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 Oct 2026.