The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification

Matthew Middlehurst; Aiden Rushbrooke; Ali Ismail-Fawaz; Maxime Devanne; Germain Forestier; Angus Dempster; Geoffrey I. Webb; Christopher Holder

cs.LGMar 20, 2026

The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification

Authors: Matthew Middlehurst, Aiden Rushbrooke, Ali Ismail-Fawaz, Maxime Devanne, Germain Forestier, Angus Dempster, Geoffrey I. Webb, Christopher Holder,

Organizations: University of Bradford · University of East Anglia · Université de Haute-Alsace · Monash University ·

Abstract

Time series machine learning (TSML) is a growing research field that spans a wide range of tasks. The popularity of established tasks such as classification, clustering, and extrinsic regression has, in part, been driven by the availability of benchmark datasets. An archive of 30 multivariate time series classification datasets, introduced in 2018 and commonly known as the UEA archive, has since become an essential resource cited in hundreds of publications. We present a substantial expansion of this archive that more than quadruples its size, from 30 to 133 classification problems. We also release preprocessed versions of datasets containing missing values or unequal length series, bringing the total number of datasets to 147. Reflecting the growth of the archive and the broader community, we rebrand it as the Multiverse archive to capture its diversity of domains. The Multiverse archive includes datasets from multiple sources, consolidating other collections and standalone datasets into a single, unified repository. Recognising that running experiments across the full archive is computationally demanding, we recommend a subset of the full archive called Multiverse-core (MV-core) for initial exploration. To support researchers in using the new archive, we provide detailed guidance and a baseline evaluation of established and recent classification algorithms, establishing performance benchmarks for future research. We have created a dedicated repository for the Multiverse archive that provides a common aeon and scikit-learn compatible framework for reproducibility, an extensive record of published results, and an interactive interface to explore the results.

Figures & tables

Year	arXiv	Journal	Total	ML	Conv	RNN	Graph	Transf	Found	Deep
2019	12	0	3	0	2	0	0	1	0	0
2020	33	0	8	4	1	0	0	3	0	0
2021	72	28	12	6	3	2	0	0	1	0
2022	99	100	18	4	2	1	2	7	2	0
2023	138	173	15	3	3	0	1	6	1	1
2024	197	174	39	6	4	1	5	12	7	4

Table 1: Counts of papers roughly classified into one of the categories ML (machine learning), Conv (primarily CNN based for classification), Graph (learn structure on a graph representation), Transf (transformer based architecture using, e.g. attention or masking), foundation (model proposed as a backbone for multiple tasks which may be pretrained).

Year	No. papers	No. with code	No. datasets	Average	Algorithms	Average
2019	3	2	26–30	28.5	8–8	8.0
2020	8	2	6–30	15.1	2–16	6.6
2021	12	7	1–30	19.2	1–15	7.5
2022	18	15	4–30	19.0	1–14	7.9
2023	15	6	3–30	17.3	3–12	7.1
2024	39	19	3–30	21.4	3–19	10.3

Table 2: Estimates of the number of datasets and the number of algorithms used in papers using the UEA archive to support new MTSC algorithms.

Dataset	HC2	TimesNet	ConvTran	TapNet	LiteMVTime	ShapeNet
ArticularyWordRecognition	0.993	0.973	0.983	0.987	0.973	0.987
AtrialFibrillation	0.267	0.333	0.4	0.333	0.133	0.4
BasicMotions	1	0.973	1	1	1	1
Cricket	1	0.903	1	0.958	0.986	0.986
DuckDuckGeese	0.56	0.58	0.62	0.575	0.18	0.725
Epilepsy	1	0.877	0.985	0.971	0.993	0.987

Table 3: Published accuracy on the default test split of six classifiers proposed in the last five years on the 25 UEA datasets common to all papers. Classifiers are: ML algorithm HIVE-COTEv2 (HC2) Middlehurst et al. (2021) ; Foundation backbone TimesNet Wu et al. (2023) , Transformer approach ConvTran Foumani et al. (2024c) ; Convolutional approaches TapNet Zhang et al. (2020) and LiteMVTime Ismail-Fawaz et al. (2023b) ; and deep learning algorithm ShapeNet Li et al. (2021) . Best results in bold.

$\leq$ 200 41 (30.83%) 201-2000 51 (38.35%) 2001-20000 23 (17.29%) $>$ 20000 18 (13.53%) Minimum 12 Maximum 47,328,752	$\leq$ 200 60 (45.11%) 201-2000 37 (27.82%) 2001-20000 23 (17.29%) $>$ 20000 13 (9.77%) Minimum 4 Maximum 11,940,071	2 67 (50.38%) 3-5 38 (28.57%) 6-15 19 (14.29%) $>$ 15 9 (6.77%) Minimum 2 Maximum 39
(a) Train Size	(b) Test Size	(c) No. Classes
$\leq$ 50 16 (12.03%) 51-500 76 (57.14%) 501-5000 37 (27.82%) $>$ 5000 4 (3.01%) Minimum 8 Maximum 17,984 $\leq$ 5 28 (21.05%) 6-20 43 (32.33%) 21-100 53 (39.85%) $>$ 100 9 (6.77%) Minimum 2 Maximum 1345 (d) No. Time points (e) No. Channels
Clean 119 (89.47%) Unequal Length 9 (6.77%) Missing Values 5 (3.76%) Audio 6 (4.51%) Biosignal 37 (27.82%) Digital 2 (1.50%) Motion 65 (48.87%) Image 7 (5.26%) Power 3 (2.26%) Sensor 11 (8.27%) Spectro 2 (1.50%) (f) Series Cleanliness (g) Dataset Types

Table 4: Summary statistics for the 133 multivariate archive datasets, excluding missing value and unequal length variants. Provides statistics for the train set sizes (a), test set sizes (b), number of classes (c), number of time points (d) and number of dimensions (e) of the archive datasets. Also includes counts for series cleanliness before processing (f) and dataset type (g).

Dataset name	Train	Test	Channels	Length	Classes	Type
ArticularyWordRecognition	275	300	9	144	25	Motion
AtrialFibrillation	15	15	2	640	3	Biosignal
BasicMotions	40	40	6	100	4	Motion
CharacterTrajectories	1422	1436	3	60-182	20	Motion
Cricket	108	72	6	1197	12	Motion
DuckDuckGeese	50	50	1345	270	5	Audio

Table 5: The original 30 MTSC archive datasets. For datasets with unequal length series, both the minimum and maximum series lengths are shown.

Dataset name	Train	Test	Channels	Length	Classes	Type
Alzheimers	45	43	19	15000	3	Biosignal
Blink	500	450	4	510	2	Biosignal
ButtonPress	120	120	32	1000	2	Biosignal
EyesOpenShut	56	42	14	128	2	Biosignal
FeedbackButton	1700	1150	61	450	2	Biosignal
FeetHands	2835	1890	64	640	2	Biosignal

Table 6: The 20 new MTSC archive datasets from the EEG/MEG classification archive multivariate datasets, all of type Biosignal.

Dataset name	Train	Test	Channels	Length	Classes	Type
CrowdSourced	9,456	2,833	14	256	2	Biosignal
DREAMERA	140,638	29,608	14	256	2	Biosignal
DREAMERV	140,638	29,608	14	256	2	Biosignal
FordChallenge	29,003	7,254	30	40	2	Sensor
LenDB	983,483	261,459	3	540	2	Sensor
Opportunity	12,184	5,202	113	100	5	Motion

Table 7: The 18 new MTSC archive datasets from the Monash Monster archive multivariate datasets.

Figure 1: Given a skeleton sequence of

F

frames, where each frame contains

J

joints described by

D

-dimensional features, the sequence is represented as a multivariate time series of length

F

with

J\cdot D

channels.

Repository	Subjects	Ex.	Joints	Dim.	Ch.	Notes
IRDS	29	9	25	3	75	Binary, one dataset per exercise
KERAAL	11	3	11	7	77	Binary and multiclass, 6 total
KIMORE	71	5	18	3	54	Regression reformulated as binary classification
KINECAL	–	4	25	3	75	Binary clinical risk prediction
SPHERE	6	1	15	3	45	Anomaly detection reformulated as binary classification
UCDHE	106	2	8	2	16	Binary and multiclass, 4 total

Table 8: Summary of the Rehab-Pile dataset repositories included in the Multiverse archive.

Dataset name	Train	Test	Channels	Length	Classes	Type
IRDS-EFL	223	26	75	60	2	Motion
IRDS-EFR	256	15	75	75	2	Motion
IRDS-SAL	213	56	75	82	2	Motion
IRDS-SAR	218	33	75	76	2	Motion
IRDS-SFE	237	15	75	95	2	Motion
IRDS-SFL	253	116	75	111	2	Motion

Table 9: The 39 new MTSC archive datasets from the classification portion of the Rehab-Pile archive, all of type Motion.

Dataset name	Train	Test	Channels	Length	Classes	Type
AppliancesEnergy_disc	95	42	24	144	2	Power
AustraliaRainfall_disc	112,186	48081	3	24	4	Sensor
BIDMC32HR_disc	5550	2399	2	4000	3	Biosignal
BIDMC32RR_disc	5471	2399	2	4000	3	Biosignal
BIDMC32SpO2_disc	5550	2399	2	4000	2	Biosignal
BeijingPM10Quality_disc	11,918	5048	9	24*	2	Sensor

Table 10: The 15 MTSC archive datasets from the discretised regression archive. For datasets with unequal length series, both the minimum and maximum series lengths are shown. HouseholdPowerConsumption is compressed to HPC for formatting.

Panel of Figure 2 — Figure 2: The original target labels for the discretised regression problems. The targets for each case have been sorted and plotted in a scatter graph for each problem. The colour of each point represents its post-discretisation class, showing where class splits were made and the resulting class distribution.

Dataset name	Train	Test	Channels	Length	Classes	Type
AsphaltObstaclesCoordinates	390	391	3	111-736	4	Motion
AsphaltPavementTypeCoordinates	1055	1056	3	66-2371	3	Motion
AsphaltRegularityCoordinates	751	751	3	66-4201	2	Motion
AutomotiveRoadTrials	153	77	8	300	2	Sensor
BoneIntensitiesAgeGroup	600	445	8	270	3	Image
BoneProbAgeGroup	600	445	8	256	3	Image

Table 11: The 11 new standalone MTSC archive datasets. For datasets with unequal length series, both the minimum and maximum series lengths are shown.

Panel of Figure 3 — Figure 3: An example hand X-ray, with the regions of interest around each of the phalanges of the middle finger (A). An example of a bone segmentation being converted into a univariate series (B). Images from the original PhD thesis Davis (2013) , all credit the author.

Panel of Figure 4 — Figure 4: Photo examples of the device used to record data (A) and the type of road conditions present in the different street classes from the AsphaltPavementTypeCoordinates dataset (B). This figure is borrowed from Figure 1 and 3 of Souza (2018) which introduced the data. All credit to the original authors.

Panel of Figure 5 — Figure 5: Illustration of the surface electromyography (sEMG) (A) and angle (B and C) sensors. This figure is borrowed from Figure 1 and 2 of the challenge GitHub ( https://github.com/Mvrjustid/EmoPainChallenge2020 ). All credit to the competition organisers.

Figure 6: An example of a counter movement jump split into separate stages: standing (a), preparation (b), take-off (c), flight (d), landing (e), and recovery (f). This figure is borrowed from Figure 1 of Hellmers et al. (2017) (unrelated to the source of this dataset). All credit to the original authors.

Figure 7: The classes used in TactileTextureRecognition, with visual examples of the robot arm and textures. This figure is borrowed from Figure 5 of Markert et al. (2021) . All credit to the original authors.

Dataset name	Train	Test	Channels	Length	Classes	Type
AsphaltObstaclesCoordinates_eq	390	391	3	298	4	Motion
AsphaltPavementTypeCoordinates_eq	1055	1056	3	400	3	Motion
AsphaltRegularityCoordinates_eq	751	751	3	384	2	Motion
BeijingPM10Quality_disc_nmv	11918	5048	9	24	2	Sensor
BeijingPM25Quality_disc_nmv	11918	5048	9	24	2	Sensor
BenzeneConcentration_disc_nmv	3349	5163	8	240	2	Sensor

Table 12: The 14 cleaned versions of datasets from the MTSC archive with unequal length series or missing values. This includes _eq datasets which are variants with equal length series and _nmv datasets which are variants with no missing values. HouseholdPowerConsumption is compressed to HPC for formatting.

$\leq$ 200 21 (31.82%) 201-2000 25 (37.88%) 2001-20000 15 (22.73%) $>$ 20000 5 (7.58%) Minimum 12 Maximum 112,186	$\leq$ 200 23 (34.85%) 201-2000 23 (34.85%) 2001-20000 19 (28.79%) $>$ 20000 1 (1.52%) Minimum 7 Maximum 48,081	2 23 (34.85%) 3-5 22 (33.33%) 6-15 16 (24.24%) $>$ 15 5 (7.58%) Minimum 2 Maximum 39
(a) Train Size	(b) Test Size	(c) No. Classes
$\leq$ 50 10 (15.15%) 51-500 36 (54.55%) 501-5000 17 (25.76%) $>$ 5000 3 (4.55%) Minimum 8 Maximum 17,984	$\leq$ 5 21 (31.82%) 6-20 29 (43.94%) 21-100 12 (18.18%) $>$ 100 4 (6.06%) Minimum 2 Maximum 1345	Audio 5 (7.58%) Biosignal 17 (25.75%) Motion 27 (40.91%) Image 3 (4.55%) Power 3 (4.55%) Sensor 10 (15.15%) Spectro 1 (1.52%)
(d) No. Time points	(e) No. Channels	(f) Dataset Types

Table 13: Summary statistics for the 66 Multiverse-core datasets. Provides statistics for the train set sizes (a), test set sizes (b), number of classes (c), number of time points (d), number of dimensions (e) of the archive datasets, and dataset type (f).

Figure 8: An accuracy rank critical difference diagram for multivariate-capable classifiers on 74 Multiverse datasets.

Figure 9: An MCM diagram for the top-performing multivariate-capable classifiers on 74 Multiverse datasets.

Figure 10: A scatter diagram comparing HC2 to CIF (A) and HC2 to ROCKET (B) on 74 Multiverse datasets.

Figure 11: An accuracy rank critical difference diagram for multivariate-capable classifiers on 42 Multiverse-core datasets.

Figure 12: An accuracy rank critical difference diagram for algorithms that completed all 66 Multiverse-core datasets.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset name	Train	Test	Channels	Length	Classes	Type
Alzheimers	45	43	19	15000	3	Biosignal
AppliancesEnergy_disc	95	42	24	144	2	Power
ArticularyWordRecognition	275	300	9	144	25	Motion
AsphaltObstaclesCoordinates	390	391	3	111-736	4	Motion
AsphaltObstaclesCoordinates_eq	390	391	3	298	4	Motion
AsphaltPavementTypeCoordinates	1055	1056	3	66-2371	3	Motion

Appendix

Table 14: Details for all 147 MTSC archive datasets. For datasets with unequal length series, both the minimum and maximum series lengths are shown. HouseholdPowerConsumption is compressed to HPC for formatting.

Dataset name	Classes
Alzheimers	‘0.0: 40.91%, ‘1.0: 32.95%, ‘2.0: 26.14%
AppliancesEnergy_disc	‘0.0: 71.53%, ‘1.0: 28.47%
ArticularyWordRecognition	‘1.0: 4.0%, ‘10.0: 4.0%, ‘11.0: 4.0%, ‘12.0: 4.0%, ‘13.0: 4.0%, ‘14.0: 4.0%, ‘15.0: 4.0%, ‘16.0: 4.0%, ‘17.0: 4.0%, ‘18.0: 4.0%, ‘19.0: 4.0%, ‘2.0: 4.0%, ‘20.0: 4.0%, ‘21.0: 4.0%, ‘22.0: 4.0%, ‘23.0: 4.0%, ‘24.0: 4.0%, ‘25.0: 4.0%, ‘3.0: 4.0%, ‘4.0: 4.0%, ‘5.0: 4.0%, ‘6.0: 4.0%, ‘7.0: 4.0%, ‘8.0: 4.0%, ‘9.0: 4.0%
AsphaltObstaclesCoordinates	‘raised_crosswalk: 20.49%, ‘raised_markers: 23.94%, ‘speed_bump: 27.14%, ‘vertical_patch: 28.43%
AsphaltPavementTypeCoordinates	‘cobblestone: 24.96%, ‘dirt: 36.38%, ‘flexible: 38.65%
AsphaltRegularityCoordinates	‘deteriorated: 49.27%, ‘regular: 50.73%

Appendix

Table 15: The class values for all 133 archive datasets, excluding cleaned variants. Each class value is followed by the percentage of the dataset it represents (both train and test sets concatenated). The class names used in the .ts files for each problem are displayed. HouseholdPowerConsumption is compressed to HPC for formatting.

Dataset	Label split point(s)	Split description
AppliancesEnergy	Below average usage $<15.81$ Above average usage: $\geq 15.81$	Midrange of target values
HPC1	Low consumption: $<936$ Medium consumption: $\geq 936,<2150$ High consumption: $\geq 2150$	Median of target values + and - standard deviation
HPC2	Low consumption: $<121$ Medium consumption: $\geq 121,<221$ High consumption: $\geq 221$	Median of target values + and - standard deviation
BenzeneConcentration	Below EU limit: $<5$ Above EU limit: $\geq 5$	European Union air quality standards limit of 5 $\mu g/m^{3}$ 7 7 7 https://web.archive.org/web/20241118204135/https://environment.ec.europa.eu/topics/air/air-quality/eu-air-quality-standards_en
BeijingPM25Quality	Below 2013 median: $<70$ Above 2013 median: $\geq 70$	2013 median of 74 Chinese cities from Table 1 of [ 34 ]
BeijingPM10Quality	Below 2013 median: $<108$ Above 2013 median: $\geq 108$	2013 median of 74 Chinese cities from Table 1 of [ 34 ]

Appendix

Table 16: The original target label split points used to create class labels for the discretised regression problems. HouseholdPowerConsumption is compressed to HPC for formatting.

	Arsenal	CIF	FP	HC2	MRHydra	QUANT	RDST	ROCKET
Alzheimers	0.442	0.419		0.349	0.488	0.395	0.419	0.419
AppliancesEnergy_disc	0.857	0.905	0.952	0.881	0.833	0.929	0.786	0.786
ArticularyWordRecognition	0.993	0.98	0.977	0.993	0.993	0.983	0.993	0.993
AsphaltObstaclesCoordinates_eq	0.854	0.824	0.839	0.857	0.859	0.818	0.867	0.854
AsphaltPavementTypeCoordinates_eq	0.86	0.917	0.942	0.889	0.912	0.933	0.896	0.864
AsphaltRegularityCoordinates_eq	0.936	0.977	0.991	0.971	0.988	0.988	0.983	0.939

Appendix

Table 17: Accuracy result for the top 8 classifiers from Section 6 for all 133 clean datasets. Experiments which produced no results are left blank.

	1NN-DTW	Catch22	DrCIF	Dummy	H-IT	LITETime	RIST	STC	TDE
Alzheimers	0.279	0.488	0.442	0.419	0.326	0.372	0.442	0.372	0.372
AppliancesEnergy_disc	0.643	0.881	0.905	0.81	0.524	0.738	0.905	0.857	0.81
ArticularyWordRecognition	0.987	0.983	0.987	0.04	0.99	0.983	0.987	0.973	0.993
AsphaltObstaclesCoordinates_eq	0.578	0.808	0.821	0.284	0.854	0.847	0.821	0.821	0.818
AsphaltPavementTypeCoordinates_eq	0.583	0.923	0.934	0.386	0.963	0.964	0.937	0.855	0.839
AsphaltRegularityCoordinates_eq	0.703	0.976	0.987	0.507	0.995	0.995	0.987	0.951	0.947

Appendix

Table 18: Accuracy result for the remaining classifiers from Section 6 for all 133 clean datasets. Experiments which produced no results are left blank.

Time Series Classification

Time series classification assigns labels to sequential data, using temporal patterns to support decisions in health, sensing, science, and industry.

See all 174 papers

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
Jul 7, 2026Qian Sun, Yong-Ming Tian, Jia-Wei Huang +2Synthetic Data Pretraining Multivariate Time Series Forecasting
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Intelligent Science and Technology, Nanjing University, Suzhou, China · Nanjing University – Siemens Joint Research Center on Industrial AI, Suzhou, China +1
MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification
Mar 14, 2026Celal Alagöz, Mehmet Kurnaz, Farhan AadilTime Series Classification Multiscale Time-Series Modeling
Computer Engineering, Sivas Bilim ve Teknoloji Üniversitesi, Sivas, Türkiye
TimEE: End-to-end Time Series Classification via In-Context Learning
Jul 8, 2026Jaris Küken, Shi Bin Hoo, Martin Mráz +2Synthetic Data Pretraining Time Series Classification
University of Freiburg · Zuse School ELIZA Darmstadt · Prior Labs +1

Jul 7, 2026J/K move · Enter open · S save

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

Qian Sun, Yong-Ming Tian, Jia-Wei Huang, Cheng Feng+1

State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Intelligent Science and Technology, Nanjing University, Suzhou, China · Nanjing University – Siemens Joint Research Center on Industrial AI, Suzhou, China+1

Synthetic Data Pretraining Multivariate Time Series Forecasting Zero-Shot Time Series Forecasting Time-Series Foundation Models

Open paper AskPDF arXiv

Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on multivariate synthetic data, which is easier to scale but may fail to capture the complex temporal dynamics and cross-variable relationships present in real-world time series. This raises a key question: Whether and to what extent the leading TSFMs trained with the real-world corpus perform better than those trained with synthetic data? To answer this, we establish the RMISC corpus, a considerably large-scale, high-quality, openly accessible, real-world, and multivariate time series archive that contains around 200 datasets and 142 billion time points across diverse domains. Furthermore, we pretrain four advanced TSFMs on univariate, synthetic multivariate, and real-world multivariate data and evaluate their zero-shot generalization capabilities on standard in-distribution and out-of-distribution benchmarks. Experimental results show that incorporating real-world multivariate data predominantly improves the generalization performance for both univariate and multivariate TSFMs. These results provide a deeper understanding of how real-world multivariate data contributes to the development of stronger TSFMs.

Abstract

Time Series Classification

Explore similar work

RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification

TimEE: End-to-end Time Series Classification via In-Context Learning