Effectively searching time-series data is essential for system analysis, but existing methods often require expert-designed similarity criteria or rely on global, series-level descriptions. We study language-driven segment retrieval: given a natural language query, the goal is to retrieve relevant local segments from large time-series repositories. We build large-scale segment--caption training data by applying TV2-based segmentation to LOTSA windows and generating segment descriptions with GPT-5.2, and then train a Conformer-based contrastive retriever in a shared text--time-series embedding space. On a held-out test split, we evaluate single-positive retrieval together with caption-side consistency (SBERT and VLM-as-a-judge) under multiple candidate pool sizes. Across all settings, LaSTR outperforms random and CLIP baselines, yielding improved ranking quality and stronger semantic agreement between retrieved segments and query intent.
@article{arxiv.2603.00725,
title = {LaSTR: Language-Driven Time-Series Segment Retrieval},
author = {Kota Dohi and Harsh Purohit and Tomoya Nishida and Takashi Endo and Yusuke Ohtsubo and Koichiro Yawata and Koki Takeshita and Tatsuya Sasaki and Yohei Kawaguchi},
journal= {arXiv preprint arXiv:2603.00725},
year = {2026}
}