All projects

jev-deferred-crispification

dnakhoa/jev-deferred-crispification

Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).

TeX
Stars
0
Forks
0

Why it is listed

This repository presents a research preprint about calibration across multi-step Jev-style decision pipelines and proposes “Deferred Crispification”; it is analysis, not model weights.

Related projects

  • typed-decision-bench

    Bench of typed decision models: Jev vs OpenJev vs Laya, small local LLMs and cheap hosted LLMs on the same zero-shot classification tasks, in English and French.

    Shared topics: calibration

  • jev-benchmarks

    Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

    Shared topics: calibration

  • snake-arena-jev-vs-llms

    How many decisions can a model make in a minute, and what do they cost? Jev, a System One decision model, raced against six LLMs on the same Snake boards.

    Shared topics: calibration