arXiv Machine Learning July 14, 2026 By Khalid Oublal, Quentin Bouniot, Qi Gan, Stephan Cl\'emen\c{c}on, Zeynep Akata

TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

Read the original on arXiv Machine Learning →

arXiv:2601. 09776v2 Announce Type: replace Abstract: As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and trust are essential.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jul 24

Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

arXiv:2607. 21573v1 Announce Type: cross Abstract: Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it.

By Hongnan Ma, Yiwei Shi, Mengyue Yang, Weiru Liu

benchmarks

arXiv Machine Learning

Jul 31

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

arXiv:2607. 28124v1 Announce Type: new Abstract: As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves.

By Xu Zheng, Wei Cheng, Zhuomin Chen, Mo Sha, Jingchao Ni, Dongsheng Luo

efficiency

arXiv Machine Learning

Jun 17

Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection

arXiv:2604. 17616v3 Announce Type: replace Abstract: Root cause analysis (RCA) for time-series anomaly detection is critical for the reliable operation of complex real-world systems.

By Shashank Mishra, Karan Patil, Cedric Schockaert, Didier Stricker, Jason Rambach

rag benchmarks

arXiv Machine Learning

Jun 17

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

arXiv:2606. 18049v1 Announce Type: new Abstract: Decision-making with deep learning-based time series forecasting requires not only accurate predictions but also actionable insights.

By Jan Voets, Hasan Tercan, Tobias Meisen, Sebastian Baum

benchmarks

Hugging Face Trending Papers

Jun 16

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

Decision-making with deep learning-based time series forecasting requires not only accurate predictions but also actionable insights. However, current architectures do not inherently provide such information.

benchmarks

arXiv Machine Learning

Jul 21

ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts

arXiv:2511. 02152v2 Announce Type: replace Abstract: Time series data is one of the most popular data modalities in critical domains such as industry and medicine.

By Bart{\l}omiej Ma{\l}kus, Szymon Bobek, Grzegorz J. Nalepa

benchmarks safety

Related stories

Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts