hypothesis
active
hypothesis:emotions-and-genres-will-have-structured-manifolds-behavior-and-activation-manifolds-will-be-similar-while-arbitrary-will-lack-structureEmotions and Genres will have structured manifolds, behavior and activation manifolds will be similar, while Arbitrary will lack structure
Three concrete predictions about M.
Source paper
extracted_from(2026) · Eric Bigelow · Raphaël Sarfati · Daniel Wurgaft · Owen Lewis +4
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (3)
finding
- Distance matrices of My and Mz correlate r=.71 (p<.001) for Arbitrary domain, lower similaritysupportsWeaker shared structure.
- Shared structure.
- Hierarchical structure shared.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Valence-structured manifold.
- Manifold structure is present in representations and causally influences downstream behaviorclaim0.818Interpretation of steering results.
- Generalization finding from the full paper extending beyond days-of-week to other structured concepts.
- The paper's causal explanation for why representation and behavior geometry both appear circular for days of the week.
- Extends the brutal geometry thesis beyond architecture into all creative and social domains; acknowledged as not yet confirmed with certainty
- Interpretive hypothesis offered to explain why emotion features are more persistent