AI 中文总结
MutMem V2 填补了 MutMem V1 的发布缺口，规定了相关协议规范，经多实现验证与实验支持，可支持可移植完整性等多方面声明，但不确立语义真实性等内容。
AI 中文摘要
MutMem V1 引入了持久智能体内存中保留保留性的密码学授权变异，但未提供完整的可移植验证合约或干净安装的复现路径。MutMem V2 在不引入第二个内存引擎的情况下填补了这一发布缺口，它规定了精确的规范字节、域分离的对象与承诺束、强制召回证据的成员资格与排序、外部信任锚、身份纪元、撤销、授权、请求收据、有序披露以及三种变异终端类型。发布的协议包含 18 个版本化对象模式、39 个召回向量、15 个变异向量和 37 个封闭召回失败原因。独立的 Node 和 Python 实现对全部 72 个结构和密码学终端的裁决及主要原因达成一致；生产合规语料库在 28 个要求类别中对 42/42 个案例达成一致。干净的 Node v26.8.1 安装在无实验内存的情况下达到首次启动、重启和调度器就绪状态。一个单独范围的 120 单元金丝雀实验仅支持显式标记遍历。每个公开表均可从自哈希聚合中再生，独立验证器可重构统计数据和声明边界。历史 V1 实证结果保持历史状态。MutMem V2 在规定假设下支持关于可移植完整性、授权、可追溯性、合规性和可复现性的声明；它不确立语义真实性、通用鲁棒性或独立复制能力。
英文摘要
MutMem V1 introduced retention-preserving, cryptographically authorized mutation for persistent agent memory but did not provide a complete portable verification contract or clean-install reproduction path. MutMem V2 closes that publication gap without introducing a second memory engine. It specifies exact canonical bytes, domain-separated object and bundle commitments, mandatory recall-evidence membership and ordering, external trust anchors, identity epochs, revocation, authorization, request receipts, ordered disclosure, and three mutation terminal types. The released protocol contains 18 versioned object schemas, 39 recall vectors, 15 mutation vectors, and 37 closed recall failure reasons. Independent Node and Python implementations agree on verdict and primary reason for all 72 structural and cryptographic terminals; a production-conformance corpus agrees on 42/42 cases across 28 required classes. A clean Node v26.8.1 installation reaches first-boot, restart, and scheduler readiness with no experimental memories. A separately scoped 120-unit Canary experiment supports only explicit-marker traversal. Every public table regenerates from a self-hashed aggregate, and an independent verifier reconstructs the statistics and claim boundaries. Historical V1 empirical results remain historical. MutMem V2 supports claims about portable integrity, authorization, traceability, conformance, and reproducibility under stated assumptions; it does not establish semantic truth, universal robustness, or independent replication.
Comments11 pages, 4 tables. Companion to arXiv:2608.02843. Code, installer, independent verifiers, evidence, and release artifacts: https://github.com/wallidsaydi-creator/HOM-AIMOS
