AI RESEARCH

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels

arXiv CS.AI

ArXi:2605.19092v1 Announce Type: cross Reasoning systems increasingly separate intermediate computation into private and public channels, creating evaluation cases that look similar in transcripts: independent co-derivation, direct access to private content, and indirect influence through public communication. This paper presents a counterfactual likelihood test for measuring influence between private reasoning channels.