Python
Heman10x-NGU/openJev-verdict-2.0
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
★ 306
Stars
50 forks · 5 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
21.0
Momentum / 100
see the breakdown below
49d ago
Created
last push 17d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 13.8 | last push 17d ago; decays to zero at 180 days |
| Scale | 15 | 7.2 | 306 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 21.0 | capped at 35 because growth is unmeasured |
Detail
| Topics | agentic-aibrier-scorecalibrationdecision-enginedeep-learningencoderjevmachine-learningmodernbertnon-autoregressiveonnxopenjevrlcdselective-predictionstructured-outputssystem-onetext-classificationtypesafe-aiuncertainty-quantificationwebgpu |
| Matched on | AI Agents (agentic-ai) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +11 stars over 26 days = 0.4/day |
| Lifetime average | 6.51 stars/day over 47 days |
| First seen here | 2026-10-11 |
| Last read | 5d ago |