Third-order co-skewness in fMRI is destroyed by BFM pretraining, causing poor cognition prediction; a co-skewness-preserving linear FC exceeds BFMs and raw FC.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
q-bio.NC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Subject-specific fMRI embeddings learned unsupervised from the Natural Scenes Dataset can be aligned across individuals via orthogonal rotations, supporting a shared neural geometry in visual cortex.
citing papers explorer
-
The Variance Brain Foundation Models Forgot: Third-Order Statistics Predict Cognition Where Billion-Parameter Models Fail
Third-order co-skewness in fMRI is destroyed by BFM pretraining, causing poor cognition prediction; a co-skewness-preserving linear FC exceeds BFMs and raw FC.
-
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
Subject-specific fMRI embeddings learned unsupervised from the Natural Scenes Dataset can be aligned across individuals via orthogonal rotations, supporting a shared neural geometry in visual cortex.