Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Özer, Kadir-Kaan, Ebeling, René, Enzweiler, Markus
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.17388
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914512468180992
author Özer, Kadir-Kaan
Ebeling, René
Enzweiler, Markus
author_facet Özer, Kadir-Kaan
Ebeling, René
Enzweiler, Markus
contents We introduce JuRe (Just Repair), a minimal denoising network for time series anomaly detection that exposes a central finding: architectural complexity is unnecessary when the training objective correctly implements the manifold-projection principle. JuRe consists of a single depthwise-separable convolutional residual block with hidden dimension 128, trained to repair corrupted time series windows and scored at inference by a fixed, parameter-free structural discrepancy function. Despite using no attention, no latent variable, and no adversarial component, JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404, 180 series, 17 datasets) and second on the UCR univariate archive by AUC-PR (0.198, 250 series), leading all neural baselines on AUC-PR and VUS-PR. Component ablation on TSB-AD identifies training-time corruption as the dominant factor ($Δ$AUC-PR $= 0.047$ on removal), confirming that the denoising objective, not network capacity, drives detection quality. Pairwise Wilcoxon signed-rank tests establish statistical significance against 21 of 25 baselines on TSB-AD. Code is available at the URL https://github.com/iis-esslingen/JuRe.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17388
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Back to Repair: A Minimal Denoising Network for Time Series Anomaly Detection
Özer, Kadir-Kaan
Ebeling, René
Enzweiler, Markus
Machine Learning
Artificial Intelligence
We introduce JuRe (Just Repair), a minimal denoising network for time series anomaly detection that exposes a central finding: architectural complexity is unnecessary when the training objective correctly implements the manifold-projection principle. JuRe consists of a single depthwise-separable convolutional residual block with hidden dimension 128, trained to repair corrupted time series windows and scored at inference by a fixed, parameter-free structural discrepancy function. Despite using no attention, no latent variable, and no adversarial component, JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404, 180 series, 17 datasets) and second on the UCR univariate archive by AUC-PR (0.198, 250 series), leading all neural baselines on AUC-PR and VUS-PR. Component ablation on TSB-AD identifies training-time corruption as the dominant factor ($Δ$AUC-PR $= 0.047$ on removal), confirming that the denoising objective, not network capacity, drives detection quality. Pairwise Wilcoxon signed-rank tests establish statistical significance against 21 of 25 baselines on TSB-AD. Code is available at the URL https://github.com/iis-esslingen/JuRe.
title Back to Repair: A Minimal Denoising Network for Time Series Anomaly Detection
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.17388