Experiment code for "Sustained Gradient Alignment Mediates Subliminal Learning in a Multi-Step Setting: Evidence from MNIST Auxiliary Logit Distillation Experiment"
Abstract
This release addresses reviewers' technical concerns about the experimental setup. The subliminal learning baseline performance now matches that reported by Cloud et al. (2025).
Fields of Study & Subjects
Domain Adaptation and Few-Shot Learning
Advanced Neural Network Applications
Adversarial Robustness in Machine Learning
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 19 January 2026