{"url":"/dataset/ucr-anomaly-archive","name":"UCR Anomaly Archive","full_name":null,"description_markdown":"The UCR Anomaly Archive is a collection of 250 uni-variate time series collected in human medicine, biology, meteorology and industry. The collected time series contain a few natural anomalies though the majority of the anomalies are artificial . The dataset was first used in an anomaly detection contest preceding the ACM SIGKDD conference 2021.\r\nEach of the time series contains exactly one, occasionally subtle anomaly after a given time stamp. The data before that timestamp can be considered normal.\r\nThe time series collected in the UCR Anomaly Archive can be categorized into 12 types originating from the four domains human medicine, meteorology, biology and industry. The distribution across the domains is highly imbalanced with around 64% of the times series being collected in human medicine applications, 22% in biology, 9% in industry and 5% being air temperature measurements. The time series within a single type (e.g. ECG) are not completely unique, but differ in terms of injected anomalies or a modification of the original time series through added Gaussian noise and wandering baselines. \r\n\r\nThe downloadable archive contains, among other supplemental material, a set of slides explaining the injected anomalies with examples.","description_withheld":null,"homepage":"https://www.cs.ucr.edu/%7Eeamonn/time_series_data_2018/","introduced_date":"2020-09-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/current-time-series-anomaly-detection","title":"Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress","first_author":"Renjie Wu","url":null},"license":null,"modalities":[{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"},{"name":"Time Series Anomaly Detection","url":"/task/time-series-anomaly-detection","datasets_with_task":"/datasets/task/time-series-anomaly-detection"}],"languages":[],"variants":["UCR Anomaly Archive"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/anomaly-detection-on-ucr-anomaly-archive","task":"Anomaly Detection","dataset_variant":"UCR Anomaly Archive","rows":24,"metrics":["Average F1","AUC ROC "],"first_row_in_archive_order":{"model":"Auto-Encoder with Regression (AER)","paper":"/paper/aer-auto-encoder-with-regression-for-time","metrics":{"Average F1":"0.470"},"code_links":[{"title":"signals-dev/Orion","url":"https://github.com/signals-dev/Orion"},{"title":"D3-AI/Orion","url":"https://github.com/D3-AI/Orion"},{"title":"sintel-dev/orion","url":"https://github.com/sintel-dev/orion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/time-series-anomaly-detection-on-ucr-anomaly","task":"Time Series Anomaly Detection","dataset_variant":"UCR Anomaly Archive","rows":16,"metrics":["accuracy"],"first_row_in_archive_order":{"model":"TimeVQVAE-AD","paper":"/paper/explainable-anomaly-detection-using-masked","metrics":{"accuracy":"0.708"},"code_links":[{"title":"ml4its/timevqvae-anomalydetection","url":"https://github.com/ml4its/timevqvae-anomalydetection"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/kan-ad-time-series-anomaly-detection-with","title":"KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks","date":"2024-11-01","rows_on_this_dataset":12,"code_links":1,"syntology":null},{"paper":"/paper/explainable-anomaly-detection-using-masked","title":"Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling","date":"2023-11-21","rows_on_this_dataset":16,"code_links":1,"syntology":null},{"paper":"/paper/aer-auto-encoder-with-regression-for-time","title":"AER: Auto-Encoder with Regression for Time Series Anomaly Detection","date":"2022-12-27","rows_on_this_dataset":6,"code_links":3,"syntology":null},{"paper":"/paper/is-it-worth-it-an-experimental-comparison-of","title":"Is it worth it? Comparing six deep and classical methods for unsupervised anomaly detection in time series","date":"2022-12-21","rows_on_this_dataset":6,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}