Auditability of subliminal learning is constrained by channel location, with initialization-dependent body channels allowing pre-training screens while vocabulary geometry and conditional body channels evade them.
Distillation≈early stopping? harvest- ing dark knowledge utilizing anisotropic information retrieval for overparameterized neural network
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
s-step self-distillation is optimal among spectral shrinkage estimators for s-spiked covariance matrices and necessary for optimality.
citing papers explorer
-
Channel Location Constrains the Auditability of Subliminal Learning
Auditability of subliminal learning is constrained by channel location, with initialization-dependent body channels allowing pre-training screens while vocabulary geometry and conditional body channels evade them.
-
Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
s-step self-distillation is optimal among spectral shrinkage estimators for s-spiked covariance matrices and necessary for optimality.