Evidence record 227 · automatically gathered

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation

A student model trained on pure uniform noise can still inherit its teacher's digit-classification ability, provided the two share initialization. Previous work proves this transfer is guaranteed when the teacher's learning rate is small enough, but does not explain where in the network the channel lives or what sets its capacity. Working in an MLP distillation setting on MNIST, we show these channels are not purely informational: geometric alignment gates access to the information the channel c

Record details

Published: 5 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Children & education
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (5 July 2026), “Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation,” evidence record 227, https://ethics.ai/record/227 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.