Security-token standards expose privileged transfer, freezing, recovery, and compliance mechanisms, but a mechanism does not by itself identify the legal effect being executed or the evidence and reversal obligations attached to it. We formalize in Isabelle/HOL a reference execution semantics for the six regulatory-action meanings proposed in ERC-8319: FREEZE, SEIZE, CONFISCATE, LIQUIDATE, RESTRICT, and RECOVER. The model distinguishes applied, rejected, and operational-failure outcomes and mechanizes reversal, replay, epoch, frame, case-local terminality, and receipt properties; the build has no unproved placeholders or added axioms. It proves an external-truth boundary: two concrete worlds that disagree about title, settlement, and entitlement induce the same kernel observation, so those external facts cannot be established from bound inputs. Constructive witnesses and direct mutations show reachability and falsification for the declared fault set. For one ERC-TRUST Solidity/EVM candidate, we report separately scoped Foundry, Certora, Kontrol/KEVM, mutation, deterministic-build, and runtime-identity evidence. The current publication profile qualifies all seven evidence packages and all 49 Core and 24 mandatory Supporting obligations with no partial credit; six optional obligations remain unclaimed. A mechanized abstraction relation is proved unique and functional under pinned-runtime premises, and package and row corollaries yield conditional, profile-scoped refinement theorems from hash-bound certificates. These results do not constitute a complete Isabelle-to-Solidity-to-EVM refinement theorem, compiler correctness, an audit, production readiness, or deployment verification. The contribution is a machine-checked domain semantics and a falsifiable map of what is proved, what is bounded evidence, what is assumed, and what remains open for a regulated-token execution standard.

翻译：暂无翻译