Oscillatory signals, such as vibration, carry class-discriminative information in specific frequency bands; perturbing them in raw feature space for counterfactual analysis easily destroys their temporal structure and produces physically implausible results. In this work, we introduce IMFACT (IMF-based counterfACTuals), a model-agnostic framework for generating plausible counterfactual explanations for time series classifiers that operates in the decomposition space of Empirical Mode Decomposition.
arXiv:2608. 08207v1 Announce Type: cross Abstract: Multivariate Time Series Classification (MTSC) demands models that can effectively capture complex temporal patterns across multiple scales while remaining computationally efficient.
By Pingping Liu, Muyao Wang, Zijian Zhang, Tongshun Zhang, Hao Miao, Guorui Xie, Qingliang Li, Qiuzhan Zhou
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
This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts. In high-stakes domains such as healthcare and predictive maintenance, artificial intelligence models can increase efficiency and safety.
arXiv:2607. 18748v1 Announce Type: cross Abstract: This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts.
By Annemarie Jutte, Faizan Ahmed, Jeroen Linssen, Maurice van Keulen
arXiv:2605. 20088v2 Announce Type: replace-cross Abstract: Discovering shapelets -- i.
By Seongjun Lee, Seokhyun Lee, Changhee Lee
arXiv:2606. 03631v1 Announce Type: cross Abstract: Multivariate time series classification (MTSC) is pivotal in high-stakes domains, such as clinical diagnosis and industrial fault detection, where safe deployment necessitates transparent decision-making.
By Tao Xie, Zexi Tan, Haoyi Xiao, Mengke Li, Yiqun Zhang, Yang Lu, Cuie Yang, Yiu-ming Cheung
arXiv:2602. 08638v2 Announce Type: replace-cross Abstract: As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations.
By Dezheng Wang, Tong Chen, Guansong Pang, Congyan Chen, Shihua Li, Hongzhi Yin
WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.
By Noam Major, Kathy Razmadze, Yoli Shavit
arXiv:2607. 01838v1 Announce Type: new Abstract: Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rather than individual channels.
By Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak, Mykola Pechenizkiy
The paper introduces XACT, a framework that learns sparse attribution masks over coefficients from any invertible time‑frequency transform, such as STFT, continuous wavelet transform, and discrete wavelet transform. XACT extends the virtual inspection layer approach to wavelet transforms, enabling Layer‑wise Relevance Propagation (LRP) to generate explanations in these representations. Experiments on synthetic and two real‑world datasets show that XACT produces precise, sparse, and structured explanations, often outperforming baseline methods in highlighting relevant features.
By Theresa Dahl Frehr, Francisco Pelayo, Lukas Raad, Alicia Garc\'ia Sanz, Thea Br\"usch, Tommy Sonne Alstr{\o}m
arXiv:2607. 18279v1 Announce Type: cross Abstract: Post-hoc calibration for time-series classification usually remaps output scores, but deployment decisions such as trust, abstention, and review depend on whether a confident prediction is supported by the current temporal signal.
By Filippo Cenacchi, Longbing Cao, Runze Yang