用可执行规则实现AI系统合规性验证，支持灵活配置与自动检查。
Ontological Knowledge Blocks: Executable Compliance and Profile-Based Validation for Trustworthy AI Systems
- 将法规条文转为机器可读的结构化约束，基于知识图谱进行验证。
- 4种治理配置下违规累积严格叠加，验证延迟12.6至100.3毫秒。
- 适合需要自动化合规审计的高可信AI系统开发者使用。
部署在关键数字基础设施中的智能服务需满足透明性、可问责性、公平性和可追溯性等治理要求。当前合规依赖文档描述、静态清单和人工审查，难以适应自动化AI系统。本文提出本体知识块（OKBs），一种可编程治理架构，将监管义务编译为对结构化证据图的机器可验证约束。我们形式化了包含五元组的OKB：绑定规范义务与RDF/OWL概念模式、可执行的SHACL校验规则、明确的证据要求及PROV-O溯源链接。确定性监管编译器将结构化中间表示（IR）记录转化为可组合的知识库模块，支持无需修改服务代码的配置化治理重构。我们在24次验证运行和四种治理配置下，评估了人工智能辅助的高性能计算资源分配场景。结果表明，验证具有配置敏感性，违规累计严格叠加，SHACL验证延迟为12.6至100.3毫秒，配置等价性测试确认“综合”为最全面的配置。所有成果均开源发布。
原文摘要 · Abstract (English)
AI-enabled services deployed in critical digital infrastructure are subject to governance obligations spanning transparency, accountability, fairness, and traceability. Compliance today remains documentation-centric: obligations are described in prose, audits rely on static checklists, and verification depends on manual review. Such approaches do not scale to automated AI systems. This paper introduces Ontological Knowledge Blocks (OKBs), a programmable governance infrastructure that compiles regulatory obligations into machine-checkable constraints over structured evidence graphs. We formalize an OKB as a 5-tuple that binds normative obligations to an RDF/OWL concept schema, executable SHACL validation rules, explicit evidence requirements, and PROV-O provenance links. A deterministic regulatory compiler translates structured Intermediate Representation (IR) records into composable KB modules, enabling profile-based governance reconfiguration without modifying service code. We implement two prototypes and evaluate them in an AI-assisted HPC resource allocation scenario across 24 validation runs and four governance profiles. Results demonstrate profile-sensitive validation, strictly additive violation accumulation, SHACL validation latency between 12.6 ms and 100.3 ms, and profile equivalence testing confirming Combined as the strictly most comprehensive profile. All artefacts are released as open source.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。