claim
active
claim:standard-bayesian-icl-framing-does-not-specify-concept-kinds-and-cannot-explain-similarity-structure-of-conceptsStandard Bayesian ICL framing does not specify concept kinds and cannot explain similarity structure of concepts
Motivation.
Source paper
extracted_from(2026) · Eric Bigelow · Raphaël Sarfati · Daniel Wurgaft · Owen Lewis +4
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central thesis.
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.
- Central thesis statement of the abstract.
- Prior framework explaining ICL as inference over task structure; UCCT adopts and extends the Bayesian lens
- Open theoretical problem CIMC acknowledges: precisely characterizing the representational format of perception
- Methodological hypothesis from Box 1: the pragmatic test for extending cognitive terminology.
- People who first attempted to draw the perceived structure of a configuration showed higher agreement about which transformations are structure-preserving, despite drawing different aspects of the field of centers.
- Third empirical pattern.
- Jackson's assertion that concepts encompass state and behavior that motivates them, beyond what programmers assign to datatypes
- The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.