World-Alignment.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
23 hours	Test the new instruments; fix an O(1/n) bias in the degree decomposition	YurenHao0426
	Four tests around today's additions. Two failed on first run and both were worth having. The degree decomposition left an O(1/n) residual on a field that is purely additive: excluding the diagonal makes the two-way design unbalanced, so one pass of row and column means does not remove a pure degree effect. Swept to convergence instead. At N=256 the correction moves the reported variance shares by under 0.001, so the refutation of the hubness hypothesis stands unchanged -- but the instrument that produced it now does what it claims. The other failure was the test's own scale: two random 16-dimensional subspaces of R^64 overlap above 0.7 by chance, which is why the real measurements are made at N=256 where the null sits at 1.0. Co-Authored-By: Claude <noreply@anthropic.com>
25 hours	World Alignment: unpaired cross-modal correspondence by relational ↵	Yuren Hao
	identifiability Method: scene states are sets of part states; relation fields are built within each modality and are invariant to how each side labels its own features; the cross-modal bridge is a coupling searched under an energy that is a closed-form functional of one matrix; solving is spectral initialisation followed by exact local refinement. Evidence: in a procedurally generated closed world, blind recovery of a hidden image-caption correspondence reaches 95.3% at 256 scenes against 0.39% chance, and the recovered pairs transfer to 200 held-out scenes at 93.0% exact retrieval with random-pair and shuffled-image controls at or near chance. Cross-modal value correspondence is derived from disjoint corpora rather than declared. On Visual Genome the field correlation reaches 0.656 against the 0.9 that polynomial recovery needs, with the deficit attributed away from segmentation and discretisation. Protocol: no image-text pair enters any objective, optimiser, initialisation, or model selection; hidden pairs score orderings only. Co-Authored-By: Claude <noreply@anthropic.com>