All decision model projects

Small reproducible benchmark of Jev against LLMs, fine-tuned BERT, Laya and zero-shot NLI on SST-2, AG News and Banking77.

Open framework and preprint benchmarking typed decision models such as Jev, pplx-decider, Liquid D1 and Clef in six clusters.

Metamorphic benchmark testing whether decision-model probabilities stay coherent under 50 laws, with no gold labels.

Small one-pass option scorer with n-gram encoder, rival-aware attention and temperature scaling, benchmarked head-to-head against jevlike.

Profile matching that encodes preference criteria as Clef or Jev decision vectors, retrieves with HNSW and checks rules both ways.

Jev-inspired technique scoring single-token labels with an LLM's head via vLLM to fill typed fields, with a fast Mario demo.

Benchmark asking models to forecast federal motion-to-dismiss rulings from the judge's record, scored with claim-defendant Brier metrics.

Benchmark of nine local Jev-style decision engines on Apple Silicon across English and Korean sets, with paired significance tests.

10,000-sample multimodal benchmark for decision models that return full probability distributions over declared candidates.

Tutorial to fine-tune Qwen3.5-4B into a Jev-like classifier with Unsloth on RunPod, serve via vLLM and benchmark against Jev.

Multimodal robot decision SDK: camera images plus text go to Qwen3.5-9B with a corrective head that picks the next preset arm skill.

Experimental harness for typed JSON decisions from DiffusionGemma by picking the likeliest allowed tokens from final logits.

Public benchmark of PadFlow's land-development SaaS decisions: schemas, anonymised seed rows and a runner for calibrated decision models.

Benchmark comparing Privatemode (GLM-5.3-Flash), TypeSafe Jev and Laya on speed, accuracy, calibration and cost.

Auditable reranking benchmark: Jev vs Qwen3-Reranker-0.6B on BEIR SciFact and NFCorpus for nDCG, cost per query and tail latency.

Paper and benchmark testing Jev as a zero-shot detector of AI alignment failures across 44 benchmarks and ten failure types.

Benchmark of Jev versus OpenAI structured outputs extracting smoking history from 1,000 synthetic notes.

Reproducible benchmark of SubQ Snap, TypeSafe Jev and three open decision models on software-engineering decisions.

Benchmark of Jev on 159 community-reconstructed questions from Indonesia's SNBT 2025 university entrance exam, all responses published.

Independent head-to-head benchmark of System One decision models on one sealed manifest, from Jev and Laya to 49 open-weight entries.

Benchmark where Jev steers an agent through 100 key-and-door grid puzzles, one Choice per move, scored against an exact BFS solver.

Training-free local decision layer fusing four readings from two frozen Qwen models, auto-releasing only when readings agree.

Code Mode for MCP where retrieval shortlists tools and Jev picks one or says none fits, benchmarked on several tool-use suites.

Harness where Jev plays the first StarCraft shareware mission from structured state, with recorded per-decision action probabilities.

Benchmark of LLM-native structured output (Qwen on Cerebras) versus Jev on seven application tasks: errors, latency, tokens and cost.

Browser-agent benchmark comparing WebMCP with screenshots, DOM and code execution, including a Jev + Mercury 2.5 configuration.

Independent benchmark asking whether Jev can replace an LLM reranker, on natural-language search over 6,245 YC companies, with a live demo.

Benchmark and web UI comparing dozens of zero-shot extraction and classification systems, including Jev-like engines.

First Chinese calibration benchmark for Jev-class models: accuracy, ECE, option order and script robustness.

Curated awesome list of public Jev projects, integrations and discussions, organized by decision domain with written inclusion criteria.