Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Reads one grievance about a development project and returns a structured, auditable triage decision: dangerous cases reach the right people within hours, routine cases route automatically when the system is confident.
How it uses Jev
Jev answers 23 narrow questions as calibrated probabilities in one request, covering project match, harm, issue labels, reprisal, threat to life, confidentiality, urgency and robustness. Versioned thresholds turn probabilities into booleans, and plain Python applies policy rules P1–P8; no LLM output can change a decision.
Primitives:choicescorenoul
Technique worth stealing
Split compound concepts into single snap judgments, then combine them in code; keep dates, counts and arithmetic out of the model.
Try it
triage one samples/test1.json, or triage --cache replay one samples/test1.json offline.
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 material0.92
- Shows a System One patternFound in material0.99
- Describes handling uncertaintyFound in material0.95
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolunclear0.58
- Top-10 learning shortlist signalFound in material0.83
- Is a replica of the modelnot found in the excerpt0.05
- 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 23 Oct 2026.