mlsanityData to 7 Oct 2026

Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series

arXiv 2010.05073 ↗First posted 10 Oct 2020cs.LG cs.DBcited by 56

Not on the map. Why?

Abstract (arXiv)

Access to high-quality data repositories and benchmarks have been instrumental in advancing the state of the art in many experimental research domains. While advanced analytics tasks over time series data have been gaining lots of attention, lack of such community resources severely limits scientific progress. In this paper, we present Exathlon, the first comprehensive public benchmark for explainable anomaly detection over high-dimensional time series data. Exathlon has been systematically constructed based on real data traces from repeated executions of large-scale stream processing jobs on an Apache Spark cluster. Some of these executions were intentionally disturbed by introducing instances of six different types of anomalous events (e.g., misbehaving inputs, resource contention, process failures). For each of the anomaly instances, ground truth labels for the root cause interval as well as those for the extended effect interval are provided, supporting the development and evaluation of a wide range of anomaly detection (AD) and explanation discovery (ED) tasks. We demonstrate the practical utility of Exathlon's dataset, evaluation methodology, and end-to-end data science pipeline design through an experimental study with three state-of-the-art AD and ED techniques.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 9; 2024: 12; 2025: 13; 2026: 11.

56 papers.

Sort:

By area:

  1. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  2. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  3. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
  4. 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 58
  5. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  6. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 39
  7. 2023ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detectioncited by 38
  8. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 37
  9. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 26
  10. 2023Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Seriescited by 24
  11. 2023TSGBench: Time Series Generation Benchmarkcited by 24
  12. 2024TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Modelscited by 22
38 more
  1. 2024See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzerscited by 20
  2. 2022Sintel: A Machine Learning Framework to Extract Insights from Signalscited by 16
  3. 2022A Comparative Study on Unsupervised Anomaly Detection for Time Series: Experiments and Analysiscited by 10
  4. 2026SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarioscited by 8
  5. 2025When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Seriescited by 7
  6. 2025Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedbackcited by 7
  7. 2024Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Datasetcited by 6
  8. 2025mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scalecited by 6
  9. 2025Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Servicescited by 6
  10. 2022Trustworthy Anomaly Detection: A Surveycited by 5
  11. 2022A Meta-level Analysis of Online Anomaly Detectorscited by 5
  12. 2025xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detectioncited by 5
  13. 2025MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysiscited by 4
  14. 2023BALANCE: Bayesian Linear Attribution for Root Cause Localizationcited by 3
  15. 2024Anomaly Prediction: A Novel Approach with Explicit Delay and Horizoncited by 3
  16. 2024Matrix Profile for Anomaly Detection on Multidimensional Time Seriescited by 3
  17. 2023SoftED: Metrics for Soft Evaluation of Time Series Event Detectioncited by 2
  18. 2026Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automationcited by 2
  19. 2022Explainable multi-class anomaly detection on functional datacited by 1
  20. 2023OrionBench: Benchmarking Time Series Generative Models in the Service of the End-Usercited by 1
  21. 2023EdgeConvFormer: Dynamic Graph CNN and Transformer based Anomaly Detection in Multivariate Time Seriescited by 1
  22. 2024Benchmarking Anomaly Detection Algorithms: Deep Learning and Beyondcited by 1
  23. 2024Toward a Realistic Benchmark for Out-of-Distribution Detectioncited by 1
  24. 2024Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classificationcited by 1
  25. 2025MSAD: A Deep Dive into Model Selection for Time series Anomaly Detectioncited by 1
  26. 2025A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detectioncited by 1
  27. 2026Bridging Temporal and Textual Modalities: A Multimodal Framework for Automated Cloud Failure Root Cause Analysiscited by 1
  28. 2026Benchmarking Anomaly Detection Across Heterogeneous Cloud Telemetry Datasetscited by 1
  29. 2021Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learningcited by 0
  30. 2022Statistics and Deep Learning-based Hybrid Model for Interpretable Anomaly Detectioncited by 0
  31. 2023Algorithmic Recourse in Abnormal Multivariate Time Seriescited by 0
  32. 2024Topological Analysis for Detecting Anomalies (TADA) in Time Seriescited by 0
  33. 2024MIXAD: Memory-Induced Explainable Time Series Anomaly Detectioncited by 0
  34. 2025A Radon-Nikod'ym Perspective on Anomaly Detection: Theory and Implicationscited by 0
  35. 2025Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domainscited by 0
  36. 2025ShaTS: A Shapley-based Explainability Method for Time Series Artificial Intelligence Models applied to Anomaly Detection in Industrial Internet of Thingscited by 0
  37. 2025CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environmentscited by 0
  38. 2026Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detectioncited by 0

50 most cited of 56 All 56 (JSON)