Technical Report v1.7: Axis5 Collapse Intensity and Tier3 State Distribution by Axis1 Polarity Across Four AI Upscaling Architectures

This document is the technical specification and empirical results report for DOI 1.7 of the Merutan Theory series. It covers two pieces of the Egg Model framework not addressed by the existing DOI series: (1) Axis5 (Mahalanobis-based collapse intensity) feature weights for four architecturally distinct AI super-resolution models, and (2) the Tier3 state distribution restricted to the Positive Axis1 region — a cross-tabulation of Axis1 (DOI 1.3) and Tier3 (DOI 1.2) that neither prior report performs. Axis1 polarity itself (Type A / Type B classification) is documented in DOI 1.3, and the Silent/Near-Silent/Visible/Hidden collapse summary is documented in DOI 1.2; both are already published with full four-model coverage and are intentionally not repeated here. All experiments use 5,004 ground-truth images from the NIH ChestX-ray8 database, yielding 81,975,528 blocks per model across four AI upscaling architectures. Every figure in Section 4 was independently re-derived from the source databases on 2026-07-16, including SwinIR. Dataset and Mandatory Citation:- Source: NIH ChestX-ray8 (Hospital-scale chest x-ray database)- Citation: Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017). "ChestX-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thoracic diseases." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3462–3471. - Download: https://nihcc.app.box.com/v/ChestXray-NIHCC Contact : s.shiny.n.works@gmail.com