Flattening vs. Tangling: Negative-Eigenvalue Geodesic Curvature Separates Generalization from Memorization Where Linear Effective Rank Fails

Geometric and empirical demonstration that negative-eigenvalue geodesic curvature g3 on connectivity-guaranteed MST+kNN hidden-activation graphs cleanly separates neural network generalization (monotonic manifold flattening, -43% to -73%) from random-label memorization (active manifold tangling, +11% to +75%) across ResNet-CNNs and 5-seed MLPs (>7 sigma separation, robust across neighborhood scales k) where linear covariance rank and Shannon effective rank fail or invert by up to 2.8x. Direct audits of memorized training clouds uncover intermediate-layer training tangling and a label-free readout Train-Test curvature gap (Delta g3 > 0.54), alongside two-stage asymmetric flattening in grokking.

Authors

Publication Details

Journal
Figshare
Published
2026-11-20
DOI
https://doi.org/10.6084/m9.figshare.35074318
Primary Topic
Neural Networks and Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Flattening vs. Tangling: Negative-Eigenvalue Geodesic Curvature Separates Generalization from Memorization Where Linear Effective Rank Fails

Shoji Fujita
Figshare
Neural Networks and Applications
preprint

Flattening vs. Tangling: Negative-Eigenvalue Geodesic Curvature Separates Generalization from Memorization Where Linear Effective Rank Fails

Shoji Fujita
preprint en

Abstract

Geometric and empirical demonstration that negative-eigenvalue geodesic curvature g3 on connectivity-guaranteed MST+kNN hidden-activation graphs cleanly separates neural network generalization (monotonic manifold flattening, -43% to -73%) from random-label memorization (active manifold tangling, +11% to +75%) across ResNet-CNNs and 5-seed MLPs (>7 sigma separation, robust across neighborhood scales k) where linear covariance rank and Shannon effective rank fail or invert by up to 2.8x. Direct audits of memorized training clouds uncover intermediate-layer training tangling and a label-free readout Train-Test curvature gap (Delta g3 > 0.54), alongside two-stage asymmetric flattening in grokking.

Figshare
Neural Networks and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon