All decision model projects

Research framework (DART) testing whether Jev's probabilities are a reliable signal to answer, escalate or abstain.

Experiment training two tiny Jev-style decision models, linear recurrence versus attention, under identical conditions.

Playful experiments using Jev's Choice as a decoder: next character, next BPE token, and grammar-constrained SQL generation.

Position paper arguing per-hop calibration does not compose in decision pipelines and proposing deferred crispification.

Jev applied to SemEval-2026 DimABSA dimensional sentiment tasks using only typed primitives, no generation or fine-tuning.

Reads Jev-style choice, yes/no and score probabilities from masked diffusion language models with shared Yes/No weights.

Research prototype testing Jev as a semantic supervisor that tells a driving policy to continue, observe, replan or defer.

34-page paper and kit on typed decision systems for agent workflows, separating observation, judgement, policy, action and verification.

Benchmark harness comparing Jev with OpenRouter models and open Jev-shaped models on accuracy, calibration, latency and cost.

Write-up testing whether Jev beats small fast LLM tiers on public and private classification, as a classifier or a filter.

Third-party check of Jev versus GPT-4o-mini and Claude Sonnet 4.5 routing 60 multilingual photo-shoot booking inquiries.

Agent harness with 100 mocked tools measuring steps to finish tasks when the LLM picks tools versus when Jev picks them.

Experiments testing Jev ideas against baselines, starting with Jev as a top-10 tool router for MCP agents on three benchmarks.

Evidence ledger auditing Jev claims, recomputing published calibration and running an 800-item difficulty-gradient study.

Factorio agent on FLE where Jev picks goals, next actions and stuck detection while code owns rules and actuation.

Research demo where Jev answers plain questions about text and a small learned head adds new questions from human feedback.

Research code using the Canopy-Jev decision model to route tokens to experts and extra recursion steps under explicit budgets.

Experiment generating chat replies character by character with Jev Choice over 98 next-character continuations.

Audit of 300 web pages for AI citability with nine Jev decisions each, checked against an LLM judge for agreement, cost and latency.

Nine-board gomoku workbench comparing how two Jev players respond to five different input representations of the board.

Text generation with Jev via cascaded Choice questions: word type, WordNet category, embedding cluster, then the word itself.

HKUST policy-tree guard with a 2B open classifier that routes each agent request or action to a leaf and classifies safety.

Same support agent and 25 rules guarded twice, by an LLM judge and by Jev, compared on accuracy, latency, cost and coverage.

Evaluation of Jev versus DeepSeek and Qwen on healthcare decision tasks: triage, diagnosis, medication, nursing and trial screening.

Portuguese study using Jev as a real-time guardrail and as a pre-evaluator for LLM-as-judge on customer-service agents.

Open lab on using Jev routing in front of Claude Code correctly: measured bugs and patch, hard fallback, completion gate.

TLA+-verified consensus kernel around Jev that may escalate but never returns a confident wrong verdict, tested on 1,680 pharmacy cases.

Word-level language model whose output layer is Jev: next-word choices, Noul-verified drafted chunks and bits-per-token evaluation.

Character-level language model built from Jev Choice over 28 options, where each option is the full hypothesis text.

Research replicating Jev-style typed decisions with open LLMs via logprobs; Qwen3.5-9B reached 94% with good calibration in ~1 s.