{"url":"/task/time-series-anomaly-detection","name":"Time Series Anomaly Detection","slug":"time-series-anomaly-detection","description_markdown":null,"categories":[{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":264,"papers_with_code":127,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/time-series-anomaly-detection-on-ucr-anomaly","slug":"time-series-anomaly-detection-on-ucr-anomaly","dataset":"UCR Anomaly Archive","dataset_url":"/dataset/ucr-anomaly-archive","rows_in_archive":16,"metrics":["accuracy"],"first_row_in_archive_order":{"model":"TimeVQVAE-AD","paper_title":"Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling","paper_url":"/paper/explainable-anomaly-detection-using-masked","paper_date":"2023-11-21","arxiv_id":"2311.12550","code_links":[{"title":"ml4its/timevqvae-anomalydetection","url":"https://github.com/ml4its/timevqvae-anomalydetection"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-kpi","slug":"time-series-anomaly-detection-on-kpi","dataset":"KPI","dataset_url":null,"rows_in_archive":1,"metrics":["AUPR","F1 Score","Recall","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-msl","slug":"time-series-anomaly-detection-on-msl","dataset":"MSL","dataset_url":"/dataset/msl","rows_in_archive":1,"metrics":["AUPR","F1 Score","Recall","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-smap","slug":"time-series-anomaly-detection-on-smap","dataset":"SMAP","dataset_url":"/dataset/smap","rows_in_archive":1,"metrics":["AUPR","F1 Score","Recall","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-smd","slug":"time-series-anomaly-detection-on-smd","dataset":"SMD","dataset_url":"/dataset/smd","rows_in_archive":1,"metrics":["AUPR","F1 score","Recall","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-swat","slug":"time-series-anomaly-detection-on-swat","dataset":"SWaT","dataset_url":null,"rows_in_archive":1,"metrics":["AUPR","F1 Score","Recall","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-wadi","slug":"time-series-anomaly-detection-on-wadi","dataset":"WADI","dataset_url":null,"rows_in_archive":1,"metrics":["AUPR","F1 Score","Recall","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}},{"leaderboard":"/sota/time-series-anomaly-detection-on-yahoo-a1","slug":"time-series-anomaly-detection-on-yahoo-a1","dataset":"Yahoo A1","dataset_url":null,"rows_in_archive":1,"metrics":["AUPR","F1 Score","precision"],"first_row_in_archive_order":{"model":"CARLA","paper_title":"CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection","paper_url":"/paper/carla-a-self-supervised-contrastive","paper_date":"2023-08-18","arxiv_id":"2308.09296","code_links":[{"title":"zamanzadeh/CARLA","url":"https://github.com/zamanzadeh/CARLA"}],"syntology":null}}],"datasets":[{"url":"/dataset/msl","name":"MSL","full_name":"Mars Science Laboratory","num_papers_in_archive":130},{"url":"/dataset/smap","name":"SMAP","full_name":"Soil Moisture Active Passive","num_papers_in_archive":127},{"url":"/dataset/ucr-anomaly-archive","name":"UCR Anomaly Archive","full_name":"","num_papers_in_archive":14},{"url":"/dataset/smd","name":"SMD","full_name":"Server Machine Dataset","num_papers_in_archive":10},{"url":"/dataset/paderbone-university-bearing-fault-benckmark","name":"Paderbone University Bearing Fault Benckmark","full_name":"","num_papers_in_archive":3},{"url":"/dataset/atms-fault-prediction","name":"ATMs fault prediction","full_name":"","num_papers_in_archive":2},{"url":"/dataset/finance","name":"Consumer Spendings","full_name":"Finance > US Economy > Consumer Spendings","num_papers_in_archive":2},{"url":"/dataset/edeniss2020","name":"edeniss2020","full_name":"EDEN ISS 2020 Telemetry Dataset","num_papers_in_archive":2},{"url":"/dataset/fedtadbench","name":"FedTADBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/odds","name":"ODDS","full_name":"Outlier Detection DataSets (ODDS)","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/time-series","name":"Time Series Analysis"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":127,"tagged_in_all":264,"items":[{"url":"/paper/aa-forecast-anomaly-aware-forecast-for","title":"AA-Forecast: Anomaly-Aware Forecast for Extreme Events","date":"2022-08-21","arxiv_id":"2208.09933","repositories_listed":9,"syntology":null},{"url":"/paper/lstm-based-encoder-decoder-for-multi-sensor","title":"LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection","date":"2016-07-01","arxiv_id":"1607.00148","repositories_listed":8,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/deep-and-confident-prediction-for-time-series","title":"Deep and Confident Prediction for Time Series at Uber","date":"2017-09-06","arxiv_id":"1709.01907","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/pypots-a-python-toolbox-for-data-mining-on","title":"PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series","date":"2023-05-30","arxiv_id":"2305.18811","repositories_listed":5,"syntology":{"n":21,"n_ran":0,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/tadgan-time-series-anomaly-detection-using","title":"TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks","date":"2020-09-16","arxiv_id":"2009.07769","repositories_listed":5,"syntology":null},{"url":"/paper/a-deep-neural-network-for-unsupervised","title":"A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data","date":"2018-11-20","arxiv_id":"1811.08055","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/end-to-end-self-tuning-self-supervised-time","title":"TSA on AutoPilot: Self-tuning Self-supervised Time Series Anomaly Detection","date":"2024-04-03","arxiv_id":"2404.02865","repositories_listed":4,"syntology":null},{"url":"/paper/deepant-a-deep-learning-approach-for","title":"DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series","date":"2018-12-19","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/aer-auto-encoder-with-regression-for-time","title":"AER: Auto-Encoder with Regression for Time Series Anomaly Detection","date":"2022-12-27","arxiv_id":"2212.13558","repositories_listed":3,"syntology":null},{"url":"/paper/anomaly-transformer-time-series-anomaly","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","date":"2021-10-06","arxiv_id":"2110.02642","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/time-series-anomaly-detection-service-at","title":"Time-Series Anomaly Detection Service at Microsoft","date":"2019-06-10","arxiv_id":"1906.03821","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/tab-unified-benchmarking-of-time-series","title":"TAB: Unified Benchmarking of Time Series Anomaly Detection Methods","date":"2025-06-22","arxiv_id":"2506.18046","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/timeseriesbench-an-industrial-grade-benchmark","title":"TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Models","date":"2024-02-16","arxiv_id":"2402.10802","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/dcdetector-dual-attention-contrastive","title":"DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection","date":"2023-06-17","arxiv_id":"2306.10347","repositories_listed":2,"syntology":null},{"url":"/paper/window-size-selection-in-unsupervised-time","title":"Window Size Selection in Unsupervised Time Series Analytics: A Review and Benchmark","date":"2023-02-04","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-for-time-series-anomaly","title":"Deep Learning for Time Series Anomaly Detection: A Survey","date":"2022-11-09","arxiv_id":"2211.05244","repositories_listed":2,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/mtgflow-unsupervised-multivariate-time-series","title":"Detecting Multivariate Time Series Anomalies with Zero Known Label","date":"2022-08-03","arxiv_id":"2208.02108","repositories_listed":2,"syntology":null},{"url":"/paper/multivariate-time-series-anomaly-detection","title":"Multivariate Time-series Anomaly Detection via Graph Attention Network","date":"2020-09-04","arxiv_id":"2009.02040","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/anomaly-detection-for-time-series-using-vae","title":"Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model","date":"2020-04-09","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/mtsbench-benchmarking-multivariate-time","title":"mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale","date":"2025-06-26","arxiv_id":"2506.21550","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-unsupervised-strategies-for","title":"Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series","date":"2025-06-25","arxiv_id":"2506.20574","repositories_listed":1,"syntology":null},{"url":"/paper/roca-robust-contrastive-one-class-time-series","title":"RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data","date":"2025-03-24","arxiv_id":"2503.18385","repositories_listed":1,"syntology":null},{"url":"/paper/kdselector-a-knowledge-enhanced-and-data","title":"KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection","date":"2025-03-16","arxiv_id":"2503.12478","repositories_listed":1,"syntology":null},{"url":"/paper/oipr-evaluation-for-time-series-anomaly","title":"OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest","date":"2025-03-03","arxiv_id":"2503.01260","repositories_listed":1,"syntology":null},{"url":"/paper/can-multimodal-llms-perform-time-series","title":"Can Multimodal LLMs Perform Time Series Anomaly Detection?","date":"2025-02-25","arxiv_id":"2502.17812","repositories_listed":1,"syntology":null},{"url":"/paper/dtaianomaly-a-python-library-for-time-series","title":"dtaianomaly: A Python library for time series anomaly detection","date":"2025-02-20","arxiv_id":"2502.14381","repositories_listed":1,"syntology":null},{"url":"/paper/vus-effective-and-efficient-accuracy-measures","title":"VUS: Effective and Efficient Accuracy Measures for Time-Series Anomaly Detection","date":"2025-02-18","arxiv_id":"2502.13318","repositories_listed":1,"syntology":null},{"url":"/paper/maat-mamba-adaptive-anomaly-transformer-with","title":"MAAT: Mamba Adaptive Anomaly Transformer with association discrepancy for time series","date":"2025-02-11","arxiv_id":"2502.07858","repositories_listed":1,"syntology":null},{"url":"/paper/federated-learning-with-reservoir-state","title":"Federated Learning with Reservoir State Analysis for Time Series Anomaly Detection","date":"2025-02-08","arxiv_id":"2502.05679","repositories_listed":1,"syntology":null},{"url":"/paper/gdformer-going-beyond-subsequence-isolation","title":"GDformer: Going Beyond Subsequence Isolation for Multivariate Time Series Anomaly Detection","date":"2025-01-30","arxiv_id":"2501.18196","repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}