CLaP - State Detection from Time Series

Summary: CLaP reframes unsupervised state detection by self-supervising a TS classifier: cross-validating classifiers on segment-labelled subsequences to quantify confusion and merge segments into latent states. Outperforms six SOTA on 405 TS with higher precision and a superior accuracy–runtime tradeoff; scalable with a Python implementation. (summarized by gpt-5-mini on Mar 13 2026)

Paper ID: 14553
Venue: VLDB
Year: 2026
Pagerank: 5.093636e-05
Overall Rank: 10,607 | 27.23%
DOI: 10.14778/3772181.3772187

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Arik Ermshaus (Humboldt University of Berlin)
2. Patrick Schäfer (Humboldt University of Berlin)
3. Ulf Leser (Humboldt University of Berlin)

BibTeX Citation

@article{ermshaus_vldb26,
        title = {{CLaP - State Detection from Time Series}},
        author = {Ermshaus, Arik and Schäfer, Patrick and Leser, Ulf},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {1},
        pages = {70--83},
        doi = {10.14778/3772181.3772187},
        url = {https://doi.org/10.14778/3772181.3772187},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 13 of 13 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
31	BIRCH: An Efficient Data Clustering Method for Very Large Databases	1996	SIGMOD	0.00050347119
148	Gorilla: A Fast, Scalable, In-Memory Time Series Database	2015	VLDB	0.00029250767
291	OPTICS: Ordering Points To Identify the Clustering Structure	1999	SIGMOD	0.00022264197
1,364	Chimp: Efficient Lossless Floating Point Compression for Time Series Databases	2022	VLDB	0.00011020069
1,579	k-Shape: Efficient and Accurate Clustering of Time Series	2015	SIGMOD	0.00010305183
1,608	Apache IoTDB: Time-series Database for Internet of Things	2020	VLDB	0.00010227331
4,379	AutoPlait: Automatic Mining of Co-evolving Time Sequences	2014	SIGMOD	6.735265e-05
5,231	Hercules Against Data Series Similarity Search	2022	VLDB	6.3068064e-05
6,784	Motiflets - Simple and Accurate Detection of Motifs in Time Series	2023	VLDB	5.7758194e-05
7,060	Interpretable Clustering of Multivariate Time Series with Time2Feat	2023	VLDB	5.714653e-05
7,421	Raising the ClaSS of Streaming Time Series Segmentation	2024	VLDB	5.6225905e-05
9,302	ISSD: Indicator Selection for Time Series State Detection	2025	SIGMOD	5.289545e-05
9,311	Time2State: An Unsupervised Framework for Inferring the Latent States in Time Series Data	2023	SIGMOD	5.289545e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,851	Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles	2022	VLDB
2	6,141	An Experimental Evaluation of Anomaly Detection in Time Series	2024	VLDB
3	4,379	AutoPlait: Automatic Mining of Co-evolving Time Sequences	2014	SIGMOD
4	9,302	ISSD: Indicator Selection for Time Series State Detection	2025	SIGMOD
5	13,360	A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning	2024	VLDB
6	4,684	Matrix Profile IV: Using Weakly Labeled Time Series to Predict Outcomes	2017	VLDB
7	5,986	AutoTSAD: Unsupervised Holistic Anomaly Detection for Time Series Data	2024	VLDB
8	9,698	TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis	2024	VLDB
9	7,421	Raising the ClaSS of Streaming Time Series Segmentation	2024	VLDB
10	9,311	Time2State: An Unsupervised Framework for Inferring the Latent States in Time Series Data	2023	SIGMOD