# PATH: A Discrete-sequence Dataset for Evaluating Online Unsupervised Anomaly Detection Approaches for Multivariate Time Series

arXiv: https://arxiv.org/abs/2411.13951 · HTML: https://mlsanity.com/paper/2411.13951/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 49 references that are in the map.
- First posted on arXiv 21 Nov 2024.

## Builds on (most cited first, 14 of 14)

- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https://mlsanity.com/paper/1811.08055/) (2018)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder](https://mlsanity.com/paper/2102.01331/) (2021)
- [Benchmarking in Optimization: Best Practice and Open Issues](https://mlsanity.com/paper/2007.03488/) (2020)
- [Do Deep Neural Networks Contribute to Multivariate Time Series Anomaly Detection?](https://mlsanity.com/paper/2204.01637/) (2022)
- [TiSAT: Time Series Anomaly Transformer](https://mlsanity.com/paper/2203.05167/) (2022)
- [Reproducibility in Machine Learning-Driven Research](https://mlsanity.com/paper/2307.10320/) (2023)
- [An Attention-based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2201.09172/) (2022)
- [Is it worth it? Comparing six deep and classical methods for unsupervised anomaly detection in time series](https://mlsanity.com/paper/2212.11080/) (2022)
- [Online Model-based Anomaly Detection in Multivariate Time Series: Taxonomy, Survey, Research Challenges and Future Directions](https://mlsanity.com/paper/2408.03747/) (2024)
- [TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-state Multivariate Time-series Data](https://mlsanity.com/paper/2407.06849/) (2024)

## Built on by (most cited first, 1 of 1)

- [DQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches](https://mlsanity.com/paper/2509.05663/) (2025)

## Abstract (arXiv)

Benchmarking anomaly detection approaches for multivariate time series is a challenging task due to a lack of high-quality datasets. Current publicly available datasets are too small, not diverse and feature trivial anomalies, which hinders measurable progress in this research area. We propose a solution: a diverse, extensive, and non-trivial dataset generated via state-of-the-art simulation tools that reflects realistic behaviour of an automotive powertrain, including its multivariate, dynamic and variable-state properties. Additionally, our dataset represents a discrete-sequence problem, which remains unaddressed by previously-proposed solutions in literature. To cater for both unsupervised and semi-supervised anomaly detection settings, as well as time series generation and forecasting, we make different versions of the dataset available, where training and test subsets are offered in contaminated and clean versions, depending on the task. We also provide baseline results from a selection of approaches based on deterministic and variational autoencoders, as well as a non-parametric approach. As expected, the baseline experimentation shows that the approaches trained on the semi-supervised version of the dataset outperform their unsupervised counterparts, highlighting a need for approaches more robust to contaminated training data. Furthermore, results show that the threshold used can have a large influence on detection performance, hence more work needs to be invested in methods to find a suitable threshold without the need for labelled data.