超越对象验证：多工件代理版本中的关系一致性
Beyond Object Validation: Relational Conformance in Multi-Artifact Agent Releases
浏览论文内容
中文总结 AI 辅助
研究多工件代理版本中软件包的关系一致性问题，通过结合Schema Docs和Brand Shuttle GEO研究故障，提出候选Schema - SIP关系一致性配置文件（SIP - RC），建模版本为图，确定故障类别并证明机制可行，完整配置文件效果待实验。
中文摘要 AI 辅助
代理系统会验证输入、工具调用和生成的对象。但最终软件包往往未受同样审查。在一次DRSS版本中，账本支持60分且证书失败，报告却宣布100分的黄金路径，每个本地关卡都是绿色，但软件包自相矛盾。我们结合Schema Docs（类似故障成为产品合同处）和Brand Shuttle GEO（证据转化为修复工作处）研究该故障。结果是候选的Schema - SIP关系一致性配置文件（SIP - RC）。它将版本建模为图，声明指向证据，决策有有限权限，派生工件保留执行条件和谱系，发布字节必须与检查的软件包匹配。硬故障不能被平均消除，验证器在单独路径上重新计算关键决策。本文确定了故障类别并表明几种机制可行。完整配置文件是否比现有检查表现更好仍是开放实验。
英文摘要
Agent systems validate inputs, tool calls, and generated objects. The final package often escapes the same scrutiny. In one DRSS release, the ledger supported 60 points and a failed certificate; the report announced a 100-point Gold Path. Every local gate was green. The package contradicted itself. We study that failure alongside Schema Docs, where similar faults became product contracts, and Brand Shuttle GEO, where evidence is turned into repair work. The result is a candidate Schema-SIP Relational Conformance profile (SIP-RC). It models a release as a graph: claims point to evidence, decisions carry bounded authority, derived artifacts retain their execution conditions and lineage, and published bytes must match the package that was checked. Hard failures cannot be averaged away, and a validator recomputes critical decisions on a separate path. The paper establishes the failure class and shows that several mechanisms are practical. Whether the full profile performs better than existing checks remains an open experiment.
