Research and benchmarks

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.

jevos is an open-source alternative to Jev for yes/no decisions that runs on your laptop.

RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

TypeLLM: LLMs with type-safe generation

The open, local take on Jev: typed decisions from an LLM, without generating a single token

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.

Train a Jev-like multimodal model by yourself. System One Model, now with vision.

Jev-compatible API endpoint based on open models (prefill-only)

AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.

Can AI agents resolve production incidents?

An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.

Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

Leaderboard that puts Jev and 14 LLMs through 108 four-option multiple-choice questions about the Convex backend platform, comparing accuracy, latency, and cost, with a per-answer explorer showing Jev probabilities.

JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.

Open Jev implementation with custom finetuning

Agentic RL 中文零基础教程（33 章）：从概念到 GRPO 实战，含 TRL 最小可跑示例；26–33 章附一套可运行的三方判别模型实证工程（encoder vs LLM-LoRA vs 规则基线）。第 25 章讲清 Jev / TypeSafe System One 与 RL 的能力边界 | Chinese Agentic RL tutorial (33 chapters) + a reproducible discriminative-model benchmark