PAI-Bench measures whether a deployed agent enacts its identity contract, and finds direct-parent identifiers in 48/48 atomic answers but 1/48 self-portraits

arXiv·medium signalXBlueskyLinkedInCopy link

A September 12 arXiv paper introduces a provider-neutral benchmark separating identity recall from composition, behavioral enactment, resistance, persistence, lineage and role-conditioned updates, with scoring oracles kept outside the target process. Two frozen campaigns over sixteen synthetic profiles, thirty-two probes and three independently initialized configurations yielded 1,536 retained responses. Explicit field cues moved joint presence of three identity identifiers from 0/8 to 7/8 under identical instructions, and replaying identical factorial responses produced a Claude headline mean 12.5 percentage points below Astra's, isolating evaluator sensitivity from target behavior.