# PATE: Proximity-Aware Time series anomaly Evaluation

arXiv: https://arxiv.org/abs/2405.12096 · HTML: https://mlsanity.com/paper/2405.12096/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 20 May 2024.

## Builds on (most cited first, 7 of 7)

- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [Towards a Rigorous Evaluation of Time-series Anomaly Detection](https://mlsanity.com/paper/2109.05257/) (2021)
- [Local Evaluation of Time Series Anomaly Detection Algorithms](https://mlsanity.com/paper/2206.13167/) (2022)
- [Precision and Recall for Time Series](https://mlsanity.com/paper/1803.03639/) (2018)
- [Personalized Anomaly Detection in PPG Data using Representation Learning and Biometric Identification](https://mlsanity.com/paper/2307.06380/) (2023)

## Built on by (most cited first, 13 of 13)

- [GenIAS: Generator for Instantiating Anomalies in time Series](https://mlsanity.com/paper/2502.08262/) (2025)
- [RATFM: Retrieval-augmented Time Series Foundation Model for Anomaly Detection](https://mlsanity.com/paper/2506.02081/) (2025)
- [TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection](https://mlsanity.com/paper/2508.00047/) (2025)
- [Quantum Gated Recurrent GAN with Gaussian Uncertainty for Network Anomaly Detection](https://mlsanity.com/paper/2510.26487/) (2025)
- [A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection](https://mlsanity.com/paper/2511.18739/) (2025)
- [Federated Learning with Reservoir State Analysis for Time Series Anomaly Detection](https://mlsanity.com/paper/2502.05679/) (2025)
- [The Emotion-Memory Link: Do Memorability Annotations Matter for Intelligent Systems?](https://mlsanity.com/paper/2507.14084/) (2025)
- [CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detection](https://mlsanity.com/paper/2509.01098/) (2025)
- [DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection](https://mlsanity.com/paper/2603.06131/) (2026)
- [CALAD: Channel-Aware contrastive Learning for multivariate time series Anomaly Detection](https://mlsanity.com/paper/2605.23139/) (2026)
- [Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems](https://mlsanity.com/paper/2607.06094/) (2026)
- [CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency](https://mlsanity.com/paper/2607.08555/) (2026)
- [Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection](https://mlsanity.com/paper/2607.11969/) (2026)

## Abstract (arXiv)

Evaluating anomaly detection algorithms in time series data is critical as inaccuracies can lead to flawed decision-making in various domains where real-time analytics and data-driven strategies are essential. Traditional performance metrics assume iid data and fail to capture the complex temporal dynamics and specific characteristics of time series anomalies, such as early and delayed detections. We introduce Proximity-Aware Time series anomaly Evaluation (PATE), a novel evaluation metric that incorporates the temporal relationship between prediction and anomaly intervals. PATE uses proximity-based weighting considering buffer zones around anomaly intervals, enabling a more detailed and informed assessment of a detection. Using these weights, PATE computes a weighted version of the area under the Precision and Recall curve. Our experiments with synthetic and real-world datasets show the superiority of PATE in providing more sensible and accurate evaluations than other evaluation metrics. We also tested several state-of-the-art anomaly detectors across various benchmark datasets using the PATE evaluation scheme. The results show that a common metric like Point-Adjusted F1 Score fails to characterize the detection performances well, and that PATE is able to provide a more fair model comparison. By introducing PATE, we redefine the understanding of model efficacy that steers future studies toward developing more effective and accurate detection models.