AI 中文总结
本文针对AI治理中评估器消失导致决策无法事后验证的问题，基于EG 3.0提出验证时间协议及VTPP，经实验验证了模型决策反转率等相关结论，明确了验证需绑定的证据与校准方法。
AI 中文摘要
AI治理与保障通常假设，由模型介导的重要决策可以事后重建或测试。但当产生该决策的评估器在相同版本和执行上下文中不再可用时，这一假设可能不成立。本文基于Execution Governance（EG）3.0开发了三种验证时间构造：决策状态承诺、独立可验证性和反事实可审计性。对发布的研究2工件的独立再处理重现了两项原始的家族内行为比较：Llama 3.1 8B与Llama 3.3 70B的模态决策反转率为52.0%（26/50），GPT-OSS 20B与GPT-OSS 120B的反转率为30.0%（15/50）。修正后的基准确定这些是家族内比较，而非提供商确立的继承关系。针对Groq指定的迁移路径进行事后重新配对后，反转率分别为64.0%和38.0%，但这些数值仍为描述性的，因为跨家族调用参数不对称。一项包含22个事件的退役普查独立重新计算得出中位值为16.45个月、均值为18.72个月、范围为3.9-40.3个月，且17/22的间隔低于24个月，同时显示评估器可用性可因服务层面而异。联合贡献是一种可操作的验证时间协议及可选的Verification-Time Preservation Package（VTPP），规定了授权时间需绑定的证据、独立可信验证者后续可证实的内容、稳定性与配对反事实测试应如何校准，以及哪些语义检查超出JSON Schema有效性范围。该协议为下游且非授权性的：它不改变EG核心公式、不添加第七个生效条件，也不规定特定司法管辖区的法律可采性。
英文摘要
AI governance and assurance often assume that a consequential model-mediated decision can be reconstructed or tested after the fact. That assumption may fail when the evaluator that produced the decision is no longer accessible in the same version and execution context. This paper develops three verification-time constructs derived from Execution Governance (EG) 3.0: Decision-State Commitment, Independent Verifiability, and Counterfactual Auditability. Independent reprocessing of released Study 2 artifacts reproduces two original within-family behavioural comparisons: 52.0% modal-decision reversal for Llama 3.1 8B versus Llama 3.3 70B (26/50) and 30.0% for GPT-OSS 20B versus GPT-OSS 120B (15/50). The corrected baseline establishes that these are within-family comparisons, not provider-established succession. Post-hoc re-pairing against Groq-designated migration paths yields 64.0% and 38.0% reversal, but these figures remain descriptive because the cross-family invocation parameters were asymmetric. A 22-event retirement census independently recomputes to median 16.45 months, mean 18.72 months, range 3.9-40.3 months, with 17/22 intervals below 24 months, while also showing that evaluator availability can differ by service surface. The joint contribution is an operational verification-time protocol and optional Verification-Time Preservation Package (VTPP) specifying what evidence to bind at authorization time, what a separately trusted verifier can substantiate later, how stability and paired counterfactual tests should be calibrated, and which semantic checks remain beyond JSON Schema validity. The protocol is downstream and non-authorizing: it does not alter the EG Core Formula, add a seventh live condition, or state jurisdiction-specific legal admissibility.
Comments25 pages, 2 figures. Publication-ready preprint v8.3. Companion evidence and baseline records are cited in the manuscript
