The Prove-Transform-Verify (PTV) Protocol for Attested Agent Identity

This document describes the Prove-Transform-Verify (PTV) protocol for hardware-anchored attestation of AI agent identity. PTV is designed to enable an agent to prove that it is running an authorized model and policy without exposing sensitive data. The protocol is intended to compose with existing RATS attestation mechanisms and to support exercise-time re-attestation requirements. The protocol defines a common envelope format (CBOR/CDDL), message types for attestation request/response, and a threat model that separates identity binding integrity from behavioral continuity. Behavioral continuity is treated as a separate requirement class addressed via exercise-time checks and execution receipts (e.g., SCITT composition), not by PTV alone. Example use cases include healthcare clinical decision support systems (CDSS), critical infrastructure industrial control systems (ICS/OT), and cross-border regulatory compliance scenarios.