SOURCE-LINKED INTELLIGENCE

Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Deep networks trained on noisy labels simultaneously generalize on clean data and memorize flipped labels. These are usually conflated as pressures on one capacity. We present Topo^2, a measurement framework that makes them causally separable, measurable, and law-governed. Persistent-homology H1 structure of the representation space separates into a within-class manifold channel (a function of the training stopping point) and a cross-class channel (a monotone readout of memorized flipped samples). An intervention, the FM0 prescription (zero loss on flipped samples from epoch 0), reaches each s

Read original source ↗ Open in workspace

recordType

paper

region

Global