| Age | Commit message (Collapse) | Author |
|---|
|
Each VG region box is index-aligned with its own description, so the crop
can be encoded and paired with the phrase describing it -- part
correspondence by annotation, which is cross-modal supervision a deployed
system would not have. The cross-modal anchor bound goes 0.336 -> 0.359.
So the two encoders do not covary at the part level either, and no
segmentation, aggregation, kernel or backbone repairs that. The 0.805
within-text ceiling was never the cross-modal ceiling; for this encoder
pair on this corpus the cross-modal ceiling is about 0.36 against the 0.9
recovery needs.
Six representational interventions this session were chosen without a
ceiling in view -- the same error being made on the matching side at the
same time. What replaces them is a three-number screening protocol that
runs before any pipeline is built.
Co-Authored-By: Claude <noreply@anthropic.com>
|
|
NATURAL_RESULTS keeps its verdict paragraph but flags that the statistic
behind it does not govern recovery, and that the search has since been
run. SYNTH_RESULTS gets a note on the parenthesis that turned out to be
the whole story: structured fields are low-rank, the threshold formula
assumes full-rank noise, and the caveat sat unfollowed for months.
Co-Authored-By: Claude <noreply@anthropic.com>
|
|
Four random resized crops per Visual Genome image, segmented
independently with their fields averaged, leave the correlation at
0.6559. Closed-world re-renders resample layout, which is nuisance by
construction, so averaging removes modality-private variation; random
crops perturb framing that self-supervised patch features already
absorb, leaving nothing to cancel.
Co-Authored-By: Claude <noreply@anthropic.com>
|
|
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>
|
