Back to Repair: A Minimal Denoising Network\ for Time Series Anomaly Detection

Hugging Face Daily Papers Papers

Summary

This paper introduces JuRe (Just Repair), a minimal denoising network for time series anomaly detection that matches or exceeds complex neural baselines on the TSB-AD and UCR benchmarks, demonstrating that a proper manifold-projection training objective is more important than architectural complexity.

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 (ΔAUC-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.
Original Article
View Cached Full Text

Cached at: 04/21/26, 07:20 AM

Paper page - Back to Repair: A Minimal Denoising Network\ for Time Series Anomaly Detection

Source: https://huggingface.co/papers/2604.17388

Abstract

JuRe, a simple denoising network for time series anomaly detection, demonstrates that architectural simplicity can match or exceed complex models when the training objective properly implements the manifold-projection principle.

We introduce JuRe (Just Repair), a minimaldenoising networkfortime series anomaly detectionthat exposes a central finding: architectural complexity is unnecessary when the training objective correctly implements themanifold-projection principle. JuRe consists of a singledepthwise-separable convolutional residual blockwith hidden dimension 128, trained to repair corrupted time series windows and scored at inference by a fixed, parameter-freestructural discrepancy function. Despite using no attention, no latent variable, and no adversarial component, JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR0.404, 180 series, 17 datasets) and second on the UCR univariate archive byAUC-PR(0.198, 250 series), leading all neural baselines onAUC-PRandVUS-PR. Component ablation on TSB-AD identifiestraining-time corruptionas the dominant factor (ΔAUC-PR= 0.047 on removal), confirming that the denoising objective, not network capacity, drives detection quality.Pairwise Wilcoxon signed-rank testsestablish statistical significance against 21 of 25 baselines on TSB-AD. Code is available at the URL https://github.com/iis-esslingen/JuRe.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2604\.17388

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2604.17388 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2604.17388 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2604.17388 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection

arXiv cs.LG

This paper proposes CoAD, a novel framework that unifies Outlier Exposure (classification) and Masked Autoencoder (reconstruction) paradigms for time series anomaly detection, addressing their respective limitations. Extensive experiments show that CoAD significantly outperforms state-of-the-art methods while being lightweight and fast.