Calibration and threshold setting with decision models

Sutro's active-learning CLI that finds rows Jev is least sure about, asks you to label them, and uses GEPA to improve the definition.

Bun harness that runs Jev over datasets via OpenRouter, streams JSONL answers, and checks calibration, stability and regressions.

TypeScript library of decision contracts, confidence thresholds, fallbacks, human review and evaluation patterns on top of the TypeSafe SDK.

TypeScript library composing Jev judgments into deterministic threshold workflows that return explainable action sets.

C++20 library for typed routing, classification and scoring with compile-time enum schemas, local Laya and optional System One.

Rust crate and jud CLI where a decision is a .jud rubric file answered by a System One model, type-checked and testable without a key.

pijev: drop-in wrapper for the TypeSafe Python SDK that averages Jev answers across option orders in one request.

Zero-dependency TypeScript wrapper for Jev where every typed decision has a required unsure branch the compiler enforces.

Self-hosted Go gateway for LLMs and decision models that prunes context, and audits and calibrates Jev or open-rlcd decisions.

Rust derive layer that turns enums and structs into Choice, Score and Noul questions with compile-checked, confidence-gated answers.

Local Jev-compatible proxy that records an app's typed decisions, distils a head per decision site on Laya, and answers when confident.

Community Rails integration for System One with configuration, persisted usage and cost telemetry, and fail-closed confidence policies.

Calculator with no arithmetic in its code: Jev picks each answer character from 13 options, exposing its distributions and jitter.

Declarative compiler that turns state, decisions and labeled examples into a measured, frozen JSON program of typed Jev questions.

Calibration experiments showing Jev's Choice probabilities on fair dice and coins stay high while accuracy stays at chance.

Learning project that builds choose-an-answer decision models from scratch and from Qwen, with downloadable 0.8B and 4B releases.

Daily arXiv and bioRxiv radar where Jev answers one yes/no per plain-English interest for every new paper; fork-and-go GitHub Action.

Runnable Jev cookbooks, a plain-English guide and sixteen interactive simulations of how a typed decision model changes architecture.

48-requirement spec and conformance suite for Jev-compatible servers, with a normalising proxy; shows confidence is not portable.

Pokémon Red on PyBoy where code owns route and arithmetic, Jev picks only at branches, and battle faint predictions are Brier-scored.

Reliability testing for typed decision models: contracts, calibration metrics, metamorphic fuzzing and CI pass/warn/fail gates.

Twenty-questions game where Jev's confidence decides when to stop: it commits, hedges or refuses to guess.

Browser-only Jev testbed via Vercel AI Gateway for building boolean, choice and score questions and viewing probabilities and cost.

Chinese 'emotion lie detector' demo comparing Jev's Choice, Score and Noul judgments on a message with a general LLM.

Chinese-language tutorial repo with six runnable Python demos and four notes on Jev primitives, with offline mock mode and live samples.

Portuguese-language Go proof of concept that tests whether Jev's confidence is calibrated enough to auto-route support tickets.

Python harness stress-testing Jev's confidence, its accuracy as a RAGTruth hallucination judge, and its use as a RAG reranker.

Measurement-first lab deciding which classifier technique, Jev, rules or other models, earns a place in a coding-agent fleet.

Family of small Jev-like decision models you can train and run yourself, with a server compatible with TypeSafe's SDK.

Local Jev alternative on zero-shot NLI models with temperature scaling and conformal abstention; reports ECE 0.170 to 0.071, offline.