Contamination Map Methodology

Time series / Model

TSPulse r1

Organisation
IBM Research
Family
Granite TimeSeries (TSPulse) · version r1
Released
2025-06-03 (HF repo creation date of ibm-granite/granite-timeseries-tspulse-r1 per HF API; arXiv v1 2025-05-19 (https://arxiv.org/abs/2505.13033v1))
Checkpoints
ibm-granite/granite-timeseries-tspulse-r1 (main = tspulse-hybrid-allhead-512-p8-r1, for anomaly detection), ibm-granite/granite-timeseries-tspulse-r1@tspulse-hybrid-dualhead-512-p8-r1, ibm-granite/granite-timeseries-tspulse-r1@tspulse-block-dualhead-512-p16-r1 (classification)
Weights
Open · apache-2.0
Links
PaperModel cardCode

Training data disclosure: Full list

Level determined for 100% of benchmark cells.

“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Other declared training data

Declared exclusions

Benchmark cells

GIFT-Eval

Not seen Jena Weather (GIFT-Eval) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen BizITObs - Application · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen BizITObs - Service · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen BizITObs - L2C · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Bitbrains - Fast Storage · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Bitbrains - rnd · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Restaurant (Recruit Restaurant Visitor Forecasting) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ETT1 (GIFT-Eval) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ETT2 (GIFT-Eval) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Loop Seattle (LibCity) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen SZ-Taxi (LibCity) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M_DENSE (LibCity) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Seen, split unclear Solar (LSTNet, 137 Alabama PV plants) · the dataset was used; the source does not say which part

Evidence (2)
“solar 10 minutes dataset + DRS”
arxiv.org · paper · Appendix A.8, Table 10 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15

Not seen Hierarchical Sales (Mancuso et al., 2020) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M4 Yearly · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M4 Quarterly · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M4 Monthly · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M4 Weekly · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M4 Daily · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen M4 Hourly · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Hospital · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen COVID Deaths · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Seen, split unclear US Births · the dataset was used; the source does not say which part

Evidence (2)
“us births dataset”
arxiv.org · paper · Appendix A.8, Table 10 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15

Seen, split unclear Saugeen River Flow · the dataset was used; the source does not say which part

Evidence (2)
“saugeenday dataset”
arxiv.org · paper · Appendix A.8, Table 10 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15

Not seen Temperature Rain · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Seen, split unclear KDD Cup 2018 · the dataset was used; the source does not say which part

Evidence (2)
“kdd cup 2018 dataset (no missing)”
arxiv.org · paper · Appendix A.8, Table 10 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15

Not seen Car Parts · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ElectricityLoadDiagrams20112014 (UCI) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Long-horizon forecasting (ETT, Electricity, Traffic, Weather, Exchange, ILI)

Not seen ETTh1 · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ETTh2 · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ETTm1 · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ETTm2 · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Electricity (ECL, 321 clients) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Traffic (PeMS San Francisco Bay, 862 sensors) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Weather (Jena, 2020; Autoformer) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Exchange-Rate · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen ILI (CDC influenza-like illness, national) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Time-series anomaly detection

Not seen TSB-AD-U (TSB-AD univariate) · the authors state the dataset was excluded from training

Evidence (2)
“All pre-training datasets are strictly disjoint from evaluation sets.”
arxiv.org · paper · Table 10 caption · retrieved 2026-10-15
“Setup: We evaluate TSPulse on the TSB-AD benchmark (Liu & Paparrizos, 2024) (recent comprehensive leaderboard for AD), which comprises 40 eval datasets, covering both univariate (TSB-AD-U) and multivariate (TSB-AD-M) anomaly detection.”
arxiv.org · paper · Section 4 · retrieved 2026-10-15

Not seen TSB-AD-M (TSB-AD multivariate) · the authors state the dataset was excluded from training

Evidence (2)
“All pre-training datasets are strictly disjoint from evaluation sets.”
arxiv.org · paper · Table 10 caption · retrieved 2026-10-15
“Setup: We evaluate TSPulse on the TSB-AD benchmark (Liu & Paparrizos, 2024) (recent comprehensive leaderboard for AD), which comprises 40 eval datasets, covering both univariate (TSB-AD-U) and multivariate (TSB-AD-M) anomaly detection.”
arxiv.org · paper · Section 4 · retrieved 2026-10-15

Not seen UCR Time Series Anomaly Archive (Hexagon ML/UCR, KDD Cup 2021) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Server Machine Dataset (SMD) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Mars Science Laboratory (MSL) telemetry anomaly dataset · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Soil Moisture Active Passive (SMAP) telemetry anomaly dataset · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Pooled Server Metrics (PSM) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Secure Water Treatment (SWaT) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Yahoo S5 Labeled Anomaly Detection Dataset (Yahoo Webscope S5) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen Numenta Anomaly Benchmark (NAB) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Time-series classification

Not seen UCR Time Series Classification Archive (2018) · absent from the complete list of training data

Evidence (3)
“The complete list of datasets employed for pre-training is provided in Table 10.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“Pre-training utilizes a subset of ∼ 1B time points drawn from the Monash (Godahewa et al., 2021) and LibCity (Wang et al., 2021; Woo et al., 2024) data collections.”
arxiv.org · paper · Appendix A.8 · retrieved 2026-10-15
“TSpulse r1 was trained on a collection of datasets as follows:”
huggingface.co · model card · Training Data · retrieved 2026-10-15

Not seen UEA Multivariate Time Series Classification Archive (2018) · the authors state the dataset was excluded from training

Evidence (1)
“Importantly, none of the UEA datasets are included in the TSPulse pre-training corpus.”
arxiv.org · paper · Appendix A.12 · retrieved 2026-10-15

Notes

~1M-parameter model for anomaly detection, classification, imputation and search; three task-specialised variants (HF revisions) pre-trained on the same ~1B-point Monash + LibCity data as TTM (Ekambaram et al., 2024). '+ DRS' = additional down-sampled resolutions. No UCR/UEA or anomaly benchmark data. Splits of the pre-training datasets are not stated. The HF card list omits kaggle web traffic and NN5 (in the paper).

Sources