Agents inspect a memory constraint's provenance in one episode out of five, and act on withdrawn rules 77% of the time.

A single-author study models supersession in inherited agent memory: a constraint true when written, since withdrawn by a newer authoritative record. Given a two-record verification budget, agents checked the provenance path in about one episode in five and produced stale-consistent decisions in 77.3%, 74.7% and 74.7% of episodes across a primary run, a fresh-wording replication and a held-out domain (arXiv 2608.25553). Re-assigning one of the two slots to the critical provenance path raised current-record-consistent decisions by 74.0, 72.7 and 61.3 points, positive in six of six models, and changed nothing when the record agreed with memory. Same budget, different allocation.