遇见数据集

Energy Decision Benchmark (EDB-P): Public Dataset v1.0

收藏
Zenodo2026-01-22 更新2026-05-26 收录
官方服务:

资源简介:

A reproducible benchmark dataset for evaluating operational readiness of AI systems in regulated energy domains. Contains 150 synthetic test cases across 6 evaluation dimensions: logical consistency, counterfactual robustness, regulatory compliance, data sufficiency detection, temporal prediction, and multi-turn coherence.

提供机构:
Zenodo
创建时间:
2026-01-20
二维码
社区交流群
二维码
科研交流群
商业服务