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
A method and working example for assigning calibrated numeric trust to each fact when an LLM wiki ingests documents, so a knowledge base can be sorted, filtered, and gated by confidence instead of vague high/medium labels.
How it uses Jev
Jev runs one parallel pass per fact, taking state (entity, source, claim text) and returning reliability (noul), importance (score), specificity (score), and kind (choice). These feed a weighted formula producing a per-fact weight, aggregated per page into frontmatter confidence.
Primitives:noulscorechoice
Technique worth stealing
Replace LLM-as-a-judge with a typed decision model: reliability is a decision, not generated text, so output is free and calibrated.
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 projectunclear0.58
- Shows a System One patternnot found in the excerpt0.35
- Describes handling uncertaintynot found in the excerpt0.14
- Reports measured numbersunclear0.54
- Is a runnable toolnot found in the excerpt0.22
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelunclear0.45
- Solves a common problem (0–2)score on a 0–2 scale1.31 / 2
- About JevFound in material0.95
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.