全部项目

jev-probe

Shoaib-Asghar/jev-probe

Testing environment for TypeSafe's Jev model. It applies controlled perturbations (typos, adversarial text, reordering) to test cases, executes real API calls, and logs the raw JSON responses to DuckDB. Includes a web dashboard to track probability shifts, latency, and cost against an LLM baseline.

Python
星标
0
派生
0

收录依据

探索框架对照 Jev 与基线语言模型在保义输入扰动下的决策一致性,记录置信度、成本与延迟指标。

项目分类

标签

相关项目

  • jev-demo

    JEV Studio is a small Next.js evaluation lab for turning natural-language input into structured signals with the Typesafe SystemOne API.

    共同主题: jev-model

  • what-the-jev

    What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.

    共同主题: jev-model

  • typed-decision-bench

    Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.

    共同主题: jev-model