Technical Report v1.19: Four-Model Video Evidence Supplement for the sigma_gt/mu_gt Discreteness Cross-Model Claims (Supplement to Technical Reports v1.16 and v1.18)

This is a supplementary release, not a correction -- no value in Technical Report v1.16 or v1.18 changes. Both reports measure a ground-truth-only quantity (sigma_gt for v1.16, mu_gt for v1.18) and state that, because it depends only on the shared GT images and not on any model's reconstruction, its discreteness is identical across all four models -- but neither report backed this specific claim with the series' usual screen-recorded, hash-verified evidence. Technical Report v1.16's text stated it as an assumption from the GT-only dependency argument, with no cross-check at all. Technical Report v1.18's text claimed an improvement -- an actual independent Standard/SwinIR comparison -- but that check was only performed via terminal output reviewed in a working session, not screen-recorded, and covered two of the four models rather than all four. This supplement closes both gaps: the identical query for each quantity, executed against all four models in one continuous screen recording per quantity, confirms byte-for-byte identical results across Standard, SwinIR, Upscayl High-Fidelity, and Digital-Art in both cases (sigma_gt: 79,321,389 blocks, 2,308,415 distinct values, avg 34.36 blocks/value; mu_gt: 80,457,746 blocks, 68,649 distinct values, avg 1,172.02 blocks/value). Both results are exactly what each quantity's definition predicts; the contribution here is closing the gap between that principle and the series' own evidentiary standard, not a new empirical finding. 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