Attractor basins in transformer hidden states unify conflict and hallucination as basin competition or absence, with geometric margin outperforming entropy for detection and a scaling law governing confident hallucination rates.
Universal one-third time scaling in learning peaked distributions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Derives α^{-1/3} scaling for generalization error in online softmax classification from boundary layers in a teacher-student model.
citing papers explorer
-
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
Attractor basins in transformer hidden states unify conflict and hallucination as basin competition or absence, with geometric margin outperforming entropy for detection and a scaling law governing confident hallucination rates.
-
A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
Derives α^{-1/3} scaling for generalization error in online softmax classification from boundary layers in a teacher-student model.