LightJev is an independent Python implementation inspired by TypeSafe AI's Jev: it trains small language backbones for typed decisions with CE/Brier losses, provides evaluation, and includes an offline demo. It does not claim to reproduce TypeSafe AI's proprietary architecture or RLCD recipe.
该仓库是受 TypeSafe AI Jev 启发的独立 Python 实现，包含 CE/Brier 训练、评测、CLI 与离线可运行 demo，并明确引用 Jev 与 NanoJev-Data，内容实质且与 TypeSafe Jev 直接相关；但未调用官方 API 或复现其专有架构。
JevalsJevals/jevals-dataIndependent benchmark data comparing TypeSafe AI's Jev (System One model) against LLMs on decision score, accuracy, calibration, cost, and latency for typed tasks.
NearCaiNearCai/JevLightA 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.
choxoschoxos/jev-reviewerUses TypeSafe AI's Jev/System One model (jev-1.13.0) to locate verbatim evidence in trial reports and supplements, supporting RoB 2, ROBINS-I, QUADAS-2 templates; files are processed locally in the browser.
