TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification

ArXi:2601.21289v2 Announce Type: replace Identifying the extent to which every temporal segment influences a model's predictions is essential for explaining model decisions and increasing transparency. While post-hoc explainable methods based on gradients and feature-based attributions have been popular, they suffer from reference state sensitivity and struggle to generalize across time-series datasets, as they treat time points independently and ignore sequential dependencies.