Paper Detail

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

Kadir-Kaan Özer, René Ebeling, Markus Enzweiler

huggingface Score 4.5

Published 2026-04-19 · First seen 2026-04-21

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{zer2026back,
  title = {Back to Repair: A Minimal Denoising Network\textbackslash{} for Time Series Anomaly Detection},
  author = {Kadir-Kaan Özer and René Ebeling and Markus Enzweiler},
  year = {2026},
  abstract = {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 n},
  url = {https://huggingface.co/papers/2604.17388},
  keywords = {denoising network, time series anomaly detection, manifold-projection principle, depthwise-separable convolutional residual block, structural discrepancy function, training-time corruption, AUC-PR, VUS-PR, pairwise Wilcoxon signed-rank tests, code available, huggingface daily},
  eprint = {2604.17388},
  archiveprefix = {arXiv},
}

Metadata

{}