JevHunt

Verdict-open-jev: Non-autoregressive decision engine on ModernBERT

Heman10x-NGU/Verdict-open-jev

VerifiedResearchDocumented

Verdict-open-jev: Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit. See Jev references and source code.

Repository description: Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground

Open GitHub ↗ Read evidence ↗ Alternatives Report a problem

NOASSERTION · Python · updated 2026-09-28 · 109 ★ · Evidence checked Sep 28, 2026

What you can build with it

Browser automationEvaluation & benchmarks

Get started

Clone the repository and follow its README for install and usage. JevHunt has not run this project.

git clone https://github.com/Heman10x-NGU/Verdict-open-jev.git

Open the README ↗

Project facts

Relationship to Jev
Research
Evidence
Documented
Language
Python
License
NOASSERTION
Origin
Original repository
Repository status
Not archived
Created
2026-09-17
Last code update
2026-09-28
GitHub stars
109
Evidence checked
Sep 28, 2026
Metadata checked
Sep 28, 2026
Check status
Up to date

Stars measure the whole repository, including work unrelated to Jev.

Evidence and scope

Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.

**OpenJev (Verdict)** is an open-source, post-trained foundational decision model designed for structured software workflows, inspired by **TypeSafe AI\'s Jev** and **Reinforcement Learning for Calibrated Decisions (RLCD)**.

Evidence commit: 30f15564821626ca5c1ad5b2638c4eb7078787dd

Discovered through: awesome-jev, github-search.

How we review →

Suggest a correction · Claim this listing · Submit a project