AI RESEARCH
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
arXiv CS.AI
•
ArXi:2601.21601v2 Announce Type: replace-cross 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 on relations: negation flips truth values, converse swaps argument order, and composition chains relations.