Jev glossary
PatternsAutoresearch feature discovery
Autoresearch
A loop that proposes questions, turns free text into numeric features, and uses model errors to improve a classical regressor.
- Category
- Patterns
- Also known as
- Autoresearch feature discovery
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 221
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The cookbook turns 2,000 WineMag tasting notes into 67 numeric columns for a CatBoost model: 38 questions became 29 Score questions (mean plus spread) and 9 Nouls. Five rounds of reading its own errors cut held-out RMSE from 3.09 predicting the mean to 1.77 across 800 unseen reviews.
Request count grows with rows rather than questions (100,000 rows means 100,000 requests per round), so the pattern fits offline feature generation more than real-time paths.
Tagspatternsresearchextraction
Related terms
Definitions that connect to this one.
Composite scoringBreak a judgment into atomic Score questions, normalize each, and combine them with weights you control in code.PatternsWeighted scoreThe Score answer computed as each level number times its probability, which is why a score can land between two levels.Answers & ConfidenceCost/quality frontierPlotting accuracy against cost and time on log scales, where up and to the left is better; cascades are designed to sit there.Evaluation & Training
From the Jev directory
Directory entries that go deeper on this term.
Turn wine tasting notes into 67 numeric columns for a CatBoost regressor: five rounds of reading its own errors cut held-out RMSE from 3.09 to 1.77 across 800 unseen reviews.
Jev CookbooksDocs#official#cookbook#research
Official
SlopCop blog post by Jonathan Ellis, published November 12, 2026, reporting a bakeoff of Jev against Gemini Decisions and OpenAI for classifying GitHub event relevance, the switch to GLiDE from Fastino Labs, and lessons on eval design.
Jev Benchmarks & EvaluationsArticle#evaluation#benchmark#research
Community
v-jev 1.4 is a Jev-style decision model on Hugging Face in 0.8B and 4B sizes, built on Qwen3.5 backbones. It returns probabilities for typed questions in one forward pass and adds value extraction and image decisions.
Jev Models & Reimplementations#open-models#classification#calibration
Community
arXiv paper presenting AbductionBench, a unified framework and taxonomy for abductive reasoning tasks, instantiated on 27 datasets across ten domains and used to evaluate eight LLMs from four model families on single-choice explanation selection.
Jev Benchmarks & EvaluationsArticle#arxiv#benchmark#evaluation
Community
Open, deterministic audit benchmark for System 1 decision models, covering calibration under label-preserving perturbations, cross-question interference, and post-hoc attribution faithfulness across five open-weight models and generative baselines.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#calibration
Community
arXiv paper evaluating 67 systems, including 47 decision models and 20 LLMs, on 43 Arabic tasks across 9 task families under a shared zero-shot protocol. Jev 1.14.0 scores 69.24 against 68.77 for Jev 1.13.0 and 71.81 for Gemma-4-31B.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#benchmark
Community
215 more matching entries in the full directory.
From the Jev AI model community
Posts from builders shipping with Jev right now.