AutonLab/TimeSeriesExam1
收藏Hugging Face2025-03-13 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/AutonLab/TimeSeriesExam1
下载链接
链接失效反馈官方服务：
资源简介：
TimeSeriesExam-1数据集是一个为评估大型语言模型（LLM）在时间序列数据理解方面的能力而设计的配置型和可扩展的多选问题考试。该数据集包含五个核心时间序列理解类别：模式识别、噪声理解、相似性分析、异常检测和因果关系分析的问题和答案对。数据集中的时间序列是由多样化的基线时间序列对象组合而成的，这些对象包括线性和非线性信号以及周期性模式。
The TimeSeriesExam-1 dataset is a configurable and scalable multiple-choice question exam designed to assess the ability of Large Language Models (LLMs) to understand time series data. It includes QA pairs across five core time series understanding categories: pattern recognition, noise understanding, similarity analysis, anomaly detection, and causality analysis. The time series in the dataset are created from a combination of diverse baseline time series objects, covering linear/non-linear signals and cyclic patterns.
提供机构：
AutonLab
