Document is current

Article History

Received: 8 September 2025

Accepted: 19 January 2026

First Online: 25 February 2026

Declarations

:

: The authors have no relevant financial or non-financial interests to disclose. The authors have no Conflict of interest to declare that are relevant to the content of this article. All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript. The authors have no financial or proprietary interests in any material discussed in this article.

: In line with the FAIR principles (Findable, Accessible, Interoperable, and Reusable), all datasets used in this study are publicly available from the University of California, Riverside (UCR) Time Series Archive (Dau et al. )( ). All datasets are also available from zenodo( ) and can be downloaded as a single zip file ( ). The source code and experimental workflows are implemented using the open-source aeon toolkit (Middlehurst et al. )( ) and the tsml-eval evaluation suite( ). KASBA is available as scikit-learn compatible estimator in aeon release 1.1 as are most of the other clustering algorithms we use. All experiments, results, and reproduction scripts for this paper are available in the repository associated with this paper( ). All code is released under the BSD 3-Clause License, and full documentation is provided to support reuse, extension, and validation by other researchers.