TSDS-Toolbox: A Toolbox for Measuring Time-Series Dataset Similarity
The paper introduces a unified benchmark framework for comparing time-series dataset similarity methods.
TSDS-Toolbox is aimed at making those comparisons systematic, reproducible, and easier to extend. The authors say it supports custom datasets, similarity methods, and downstream time-series tasks. It also evaluates both dataset-level and series-level similarity methods through integrated reducers. The toolbox is public, and the paper reports validation across diverse experimental settings. HF Daily Papers' note
TSDS-Toolbox is aimed at making those comparisons systematic, reproducible, and easier to extend. The authors say it supports custom datasets, similarity methods, and downstream time-series tasks. It also evaluates both dataset-level and series-level similarity methods through integrated reducers. The toolbox is public, and the paper reports validation across diverse experimental settings. HF Daily Papers' note
score 4