Diagnostic Benchmarks for Invariant Learning Dynamics: Empirical Validation of the Eidos Architecture
Author: Datorien L. Anderson Keywords: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) Cite as: arXiv:2602.13322 [cs.CV]
Abstract
We present the PolyShapes-Ideal (PSI) dataset, a suite of diagnostic benchmarks designed to isolate topological invariance — the ability to maintain structural identity across affine transformations — from the textural correlations that dominate standard vision benchmarks. Through three diagnostic probes (polygon classification under noise, zero-shot font transfer from MNIST, and geometric collapse mapping under progressive deformation), we demonstrate that the Eidos architecture achieves >99% accuracy on PSI and 81.67% zero-shot transfer across 30 unseen typefaces without pre-training. These results validate the “Form-First” hypothesis: generalization in structurally constrained architectures is a property of geometric integrity, not statistical scale.