Mask2Cause: Temporal Causal Discovery Beyond Causality in Mean

Excerpt

arXiv:2605.07280v2 Announce Type: replace-cross Abstract: One approach to discovering causal relationships in multivariate time series is to ask whether a variable's history improves prediction of another variable. When this improvement is measured solely by reductions in optimal squared error, the criterion misses relationships that affect the target's conditional variance without changing its conditional mean. We propose Mask2Cause, an end-to-end Transformer framework for causal discovery thro