Color distances learned from language cooccurrence statistics closely mirror those learned from image cooccurrence statistics and human perceptual distances (CIELAB)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Learning cooccurrence statistics in either vision or language domain recovers roughly the same perceptual color representationclaim0.883
  Empirical validation that PMI convergence actually occurs on real data
• PMI computed from color cooccurrences in CIFAR-10 images yields a perceptual color representation closely matching both CIELAB space and language model embeddings (SimCSE, RoBERTa)finding0.822
  Validates theoretical PMI convergence claim on real data
• CIELAB Color Spacemethod0.756
  Perceptually uniform color space used as ground truth perceptual representation in color cooccurrence experiment
• The experimental method of starting with a vision and adding color to create life in the centers has predictable results: the eleven invariants.claim0.755
  Assertion that the process yields a specific set of color qualities, listed in the chapter.
• Boundaries and hairlines, by both separating and uniting adjacent colors, intensify the light and form larger wholes.claim0.752
• The better an LLM is at language modeling, the more it aligns with vision models, and vice versa — linear relationship between language modeling score and vision-language alignmentfinding0.750
  Core cross-modal empirical result: larger and better language models align better with vision models
• Families of color, like echoes, unify the composition by creating hidden similarity among all colors.claim0.750
• Correlative methods like RSA and CKA are insufficient for determining functional similarity between neural systems; causal methods are necessaryclaim0.749
  Central motivating claim of the paper; supported by empirical comparisons showing RSA/CKA miss Markovian differences detectable by MAS.