arXiv cs.LG
· Papers
The Failures of Marginal Influence-Based Attribution Methods for Global Time Series Explanations
arXiv:2607.16236v1 Announce Type: new Abstract: Explainability methods for time series models predominantly produce flat attribution scores: they quantify the direct influence of a feature at a timestamp by a scalar. We prove that the dominant failure mode of such methods is not the scalar format itself but a fundament