Automated README summary
Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A research prototype that walks ESMO decision trees for 43 tumors across 11 specialties, using Jev for clinical judgment decisions. Returns explainable recommendations and never acts autonomously.
How it uses Jev
Jev handles clinical judgment in grey zones (Choice/Score/Noul) via spec.preguntas, chooses among ESMO-valid options with expected benefit, and checks safety/contraindications. Results feed a confidence gate; low confidence or missing data triggers questions or requires oncologist review.
Primitives:choicescorenoul
Technique worth stealing
Generic engine with per-tumor JSON specs; Jev decisions are traced layer by layer for explainability.
Try it
pip install -e . then streamlit run app.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 material0.65
- Shows a System One patternFound in material0.84
- Describes handling uncertaintyFound in material0.82
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.63
- Top-10 learning shortlist signalnot found in the excerpt0.39
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale0.97 / 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 29 Sept 2026.