Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series
Summary: Exathlon is the benchmark for explainable anomaly detection over time series, built on Spark traces with six anomaly types. Ground-truth root-cause and extended-effect labels enable AD/ED evaluation and end-to-end pipelines; demonstrated on three techniques. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Vincent Jacob (Ecole Polytechnique)
- 2. Fei Song (Ecole Polytechnique)
- 3. Arnaud Stiegler (Ecole Polytechnique)
- 4. Bijan Rad (Ecole Polytechnique)
- 5. Yanlei Diao (Ecole Polytechnique)
- 6. Nesime Tatbul (Intel; Massachusetts Institute of Technology)
BibTeX Citation
@article{jacob_vldb21,
title = {{Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series}},
author = {Jacob, Vincent and Song, Fei and Stiegler, Arnaud and Rad, Bijan and Diao, Yanlei and Tatbul, Nesime},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {11},
pages = {2613--2626},
doi = {10.14778/3476249.3476307},
url = {https://doi.org/10.14778/3476249.3476307},
year = {2021}
}
Incoming Citations (Sorted by Pagerank)
Showing 15 of 15 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,382 | TAB: Unified Benchmarking of Time Series Anomaly Detection Methods | 2025 | VLDB |
| 2 | 3,987 | Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series | 2023 | VLDB |
| 3 | 9,379 | Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domains | 2025 | VLDB |
| 4 | 10,977 | TSB-AutoAD: Towards Automated Solutions for Time-Series Anomaly Detection | 2025 | VLDB |
| 5 | 11,056 | EasyAD: A Demonstration of Automated Solutions for Time-Series Anomaly Detection | 2025 | VLDB |
| 6 | 11,300 | Time-Series Anomaly Detection: Overview and New Trends | 2024 | VLDB |
| 7 | 1,029 | Anomaly Detection in Time Series: A Comprehensive Evaluation | 2022 | VLDB |
| 8 | 6,356 | TimeEval: A Benchmarking Toolkit for Time Series Anomaly Detection Algorithms | 2022 | VLDB |
| 9 | 6,141 | An Experimental Evaluation of Anomaly Detection in Time Series | 2024 | VLDB |
| 10 | 9,170 | A Demonstration of the Exathlon Benchmarking Platform for Explainable Anomaly Detection | 2021 | VLDB |