All decision model projects

Experiment testing whether a local Qwen read via label log-probabilities can replace Jev on synthetic AIOps alert decisions.

Pre-action gate and browser agent where rules decide first, then Jev or a local Jev-compatible model, emitting allow, confirm or block.

Coding agent that runs discriminative Monte Carlo Tree Search, with Gemini proposing actions and Jev Choice and Score guiding the search.

Research implementation of Jev-style typed decisions over clinical evidence: supported, contradicted or unresolved.

Kernel coordinating several Claude Code agents on one repo: Jev rates collision risk before each write to pass, wait or escalate.

Inference-time loop where a System One judge like Jev scores a model's thought paths and picks which reasoning branch to keep.

Open Jev-class decision models on Qwen3.5 with candidate-logit readout; the 4B model reports 80.1% on JevBench's 231 items.

Embodied Minecraft agent where a typed decision plane (Jev or Liquid d1) picks grounded transitions and a kernel owns verification.

Local Jev-style decision model on Qwen3.5-4B with four stress tests that show where one-pass decisions break.

LogitTrail (formerly Mini Jev): local workbench that reads typed Choice, Noul and Score decisions from a frozen LLM's logits.

Model Kombat: a 12,000-neuron fly connectome fights Jev in mk.js, with Jev picking one of seven moves about five times a second.

Camera-observed cooperative drone pursuit in a MuJoCo city where each UAV's tactical move is a /v1/systemone decision.

Reproduction and stress test of a paper asking whether Jev-style probabilities stay calibrated after routing on selected examples.

OEV: 184M-parameter decision engine that scores options in one pass, reporting 0.7705 on typed-decisions and 22 ms per question.

Open System-1 (OpenJev): Apache-2.0 research models giving calibrated per-option probabilities, best is a 4.9B exp9a.

Reads typed decisions from one forward pass of PrismML's 1.75-bit Bonsai 27B under llama.cpp, using the OpenJev/SemIf logit method.

From-first-principles PyTorch reconstruction of a Jev-like architecture with typed noul, choice and score heads; random weights only.

Open JEV: local bilingual (English/Chinese) choice and binary decisions read from a frozen Qwen3-4B's next-token label distribution.

OpenPoke fork sending yes/no decisions to Jev instead of Claude Sonnet, with an A/B on cost and latency and an injection-gate attack study.

openvons (open-Jev): finite-choice decision layer for text, images and Japanese voice, with a none option and execute/confirm/reject.

Pandu: tiny local policy networks (2.9K-5K parameters) with calibrated uncertainty that fall back to a teacher when unsure.

Java (llama.cpp via FFM) and Python engines that fill boolean/enum JSON schemas in two forward passes with per-field confidence.

Independent reproduction of Jev-style decision-model post-training on MiniCPM5-2B with LoRA, a sealed holdout and stated limits.

Laptop-scale reimplementation of RL for Calibrated Decisions: parallel constrained decoding trained with GRPO and a Brier reward.

2B decision model for robots specialised in physical judgment, returning calibrated probabilities for questions like 'will the glass tip?'

Two-stage Jev control of a MuJoCo Franka Panda: choose an intent, then X/Y/Z directions and gripper, with physics-based success checks.

Chinese Slay the Spire 2 agent research: code handles rules, cheap Jev makes most choices, a stronger model takes key moments.

Jev-class decision server on an RWKV-7 1B checkpoint that reads typed answers from a constrained softmax behind /v1/systemone.

Research system that uses a safety-tuned Jev-style predictor to forecast constraint violations of a robot VLA policy and gate actions.

Preliminary SHADE-Arena study of Jev as a monitor and per-action gate for covert agent sabotage, compared with Gemini 2.5.