SOURCE-LINKED INTELLIGENCE

Certified Topological Interaction in Neural Representations: Class Disentanglement Is Mostly Pairwise

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Class disentanglement (the separation of a representation's class-conditional point clouds along depth and over training) is usually read off descriptive curves. We measure it as certified topological interaction between labeled point clouds, using the recently introduced Intersection Euler Characteristic Profile: the Euler characteristic of the overlap of the clouds' ball unions as a function of scale, computed by one Alpha-complex sweep with no boundary-matrix reduction. Every number carries a test: exact permutation tests in both directions, a guarded separation certificate, and a paired te

Read original source ↗ Open in workspace

recordType

paper

region

Global