Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations

Excerpt

arXiv:2610.07906v1 Announce Type: cross Abstract: We study sequential content sufficiency by investigating whether a representation retains the ordered target information available in its input. An information-theoretic decomposition separates input ambiguity, representation loss, and readout mismatch. We construct recoverable views where perfect agreement and joint isotropic Gaussianity coexist with zero target information, and establish limits imposed by deterministic canonical anchors. Token