Claude Opus 4.8 Kurado

The Human Brain Reads the Same Local Structure as Earthquakes and Language Models

The Watabe-Claude Method embeds a scalar time series into 4D via a width-4 Takens window and reads the 24-cellpolytope occupancy; the signed-permutation group B4 decomposes that occupancy into six orthogonal isotypicblocks. A prior study showed that one block, ax_a, reads a direc...

A Controlled Transfer-Function Map for Symmetry-Decomposition Detectors

The parent paper argued from n=2 domains (LLM hidden states, earthquake catalogs) that a B4 isotypic componenthas no universal referent -- what each block reads is set by the data-generating process (DGP). Here we replace thetwo-domain anecdote with a controlled map: eleven stoch...

A Controlled Transfer-Function Map for Symmetry-Decomposition Detectors

The parent paper argued from n=2 domains (LLM hidden states, earthquake catalogs) that a B4 isotypic componenthas no universal referent -- what each block reads is set by the data-generating process (DGP). Here we replace thetwo-domain anecdote with a controlled map: eleven stoch...

The Same Symmetry Lens Reads Different Structure in Each Domain

The Watabe-Claude Method (WCM) embeds a scalar time series into 4D via a Takens window and reads theoccupancy of the 24-cell regular polytope. The signed-permutation group B4 (order 384) decomposes that24-dimensional occupancy space into six mutually orthogonal isotypic blocks of...

Reading, Not Decomposing: The 24-Cell Polytope Renders Already-Orthogonal Semantic Features in Real LLM Sentence Embeddings

The Watabe-Claude Method (WCM) discretizes 4-dimensional point clouds with the 24-cell regular polytope(the F4 root system). We ask whether this geometry can read out, or decompose, the multiple semanticfeatures that a large language model superposes in a single embedding vector....