Automated README summary
Automatically summarized from the README on 7 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A two-step Python pipeline that parses raw .eml email files into structured JSON and classifies each as spam or ham using TypeSafe's Jev model, with a fine-tuned ONNX encoder consulted on borderline cases.
How it uses Jev
Jev answers six Noul questions per email about credential requests, rewards, time pressure, sender mismatch, link mismatch, and disguised links. Each question returns a probability; signals fire at ≥0.5. An email is spam when at least 2 signals fire (configurable). Results are written to the JSON classification block.
Primitives:noul
Technique worth stealing
Use multiple independent Noul questions in one parallel request and threshold the fired signals to make a decision.
Try it
pip install -r requirements.txt, set TYPESAFE_API_KEY in .env, then python parse_emails.py && python classify_emails.py
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 material0.88
- Shows a System One patternnot found in the excerpt0.29
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.75
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 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 7 Oct 2026.