sysadarshsysadarsh/zerosweepZeroSweep: TypeSafe Jev Triage Engine & Benchmark
An autonomous triage engine and benchmark powered by TypeSafe AI's Jev System One model, demonstrating high-speed email classification with calibrated confidence.
200
Jev RAG Benchmark
A free RAG reranking and decision-layer benchmark for TypeSafe Jev 1.13, using frozen candidate pools, paired bootstrap CIs, and calibration, comparing against NVIDIA cross-encoder and no-reranking baselines.
该仓库是一个专门针对 TypeSafe Jev 1.13 的英文 RAG 基准测试，包含冻结候选池、配对 bootstrap 置信区间、校准分析、与 NVIDIA cross-encoder 及无重排序基线的对比，并提供了完整的复现流程和真实运行结果，实质性地集成、测试并深入评估了 Jev 模型。
· 0 starsOpen on GitHub
More like this
sysadarshsysadarsh/zerosweep
JevalsJevals/jevals-dataJevals Data: Independent benchmark for TypeSafe Jev
Independent benchmark data comparing TypeSafe AI's Jev (System One model) against LLMs on decision score, accuracy, calibration, cost, and latency for typed tasks.
100CC-BY-4.0
NearCaiNearCai/JevLightJevLight: CityFlow-based Traffic Signal Control Evaluation Framework
A CityFlow-based traffic signal control framework that evaluates TypeSafe Jev and OpenAI-compatible LLM controllers alongside rule-based and reinforcement-learning baselines through the same simulation pipeline.
000MIT