Automated README summary
Automatically summarized from the README on 8 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An auditable research project for Chinese social-platform image-text risk identification, covering data governance, traditional baselines, a Qwen3-VL domain LoRA, structured evidence, and TypeSafe Jev decisions for human review.
How it uses Jev
Jev makes policy decisions on a state containing the Chinese transcript and six evidence fields produced by the LoRA Qwen model, without the Qwen final label. Its output is used for low/medium/high risk segmentation and human review, not as calibrated probability.
Primitives:choice
Technique worth stealing
Remove the Qwen final label before sending structured evidence to Jev, keeping the decision auditable.
Try it
python -m pip install -e . then social-risk demo
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 patternunclear0.43
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.20
- Is a runnable toolnot found in the excerpt0.14
- Top-10 learning shortlist signalunclear0.56
- Is a replica of the modelFound in material0.61
- Solves a common problem (0–2)score on a 0–2 scale1.78 / 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 8 Oct 2026.