Dynamics Reveals Structure: Challenging the Linear Propagation Assumption 事件

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption arXiv:2601.21601v2 Announce Type: replace-cross Abstract: Neural networks adapt through first-order parameter updates, yet it remains unclear whether such updates preserve logical coherence. We investigate the geometric limits of the Linear Propagation Assumption (LPA), the premise that local updates coherently propagate to logical consequences. To formalize this, we adopt relation algebra and study three core operations