Mask2Cause: Causal Discovery via Adjacency Constrained Causal Attention

ArXi:2605.07280v1 Announce Type: cross Leveraging deep learning for causal discovery in time series remains challenging because existing neural methods predominantly rely on component-wise architectures that fail to capture shared system dynamics or employ decoupled post-hoc graph extraction that risks overfitting to spurious correlations. We propose $\textbf{Mask2Cause}$, an end-to-end framework that recovers the underlying causal graph directly during the forecasting forward pass. Our approach.