What it is
A repository of recorded outputs and analysis scripts for probability-output experiments with Jev: fair random draws, Noul Yes/No questions, and forecast documents. For researchers and developers evaluating Jev's calibration.
How it uses Jev
Jev's Choice and Noul primitives are queried on hidden fair dice, coins, spinners, and synthetic forecast documents. The returned probabilities are compared to known reference probabilities and observed accuracy. Results are recorded and analyzed offline; no API calls in analysis.
Primitives:choicenoul
Technique worth stealing
Using inputs with known ground-truth probabilities to measure calibration drift.
Try it
python3 scripts/analyze.py
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.95
- Shows a System One patternno0.17
- Handles uncertaintyno0.04
- Measuredyes0.98
- Runnableno0.04
- Worth recommendingno0.21
- Model replicano0.04
- Problem scopescore on a 0–2 scale1.04
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.