The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes

Excerpt

arXiv:2609.10739v1 Announce Type: cross Abstract: A truth probe fitted where truthful reporting and a task's prescribed action coincide cannot distinguish those targets from its fitting labels alone. We call this failure of semantic identification perfect aliasing. In a controlled binary reporting game, truth and prescribed-action probes fitted on compliant contexts solve the same optimization. On rival contexts their labels are complements, forcing their AUROCs to sum to one; this identity hold