Datasets › SKAB

SKAB (Skoltech Anomaly Benchmark)

28 Nov 2020 archive 2025-07-28

SKAB is designed for evaluating algorithms for anomaly detection. The benchmark currently includes 30+ datasets plus Python modules for algorithms’ evaluation. Each dataset represents a multivariate time series collected from the sensors installed on the testbed. All instances are labeled for evaluating the results of solving outlier detection and changepoint detection problems.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Change Point Detection SKAB LSTMCaps NAB (standard) 27.77 Hybridization of Capsule and LSTM Networks for... — 7 Compare
Outlier Detection SKAB LSTMCaps Average F1 0.74 Hybridization of Capsule and LSTM Networks for... — 1 Compare

Papers archive 2025-07-28

2 shown of 2 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 3. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Hybridization of Capsule and LSTM Networks for unsupervised anomaly detection on multivariate data 0 2 11 Feb 2022 not harvested
Unsupervised Offline Changepoint Detection Ensembles 1 6 9 May 2021 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

GNU General Public License v3.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • SKAB

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections