NormCode: 一种用于可审计AI规划的半形式语言
NormCode: A Semi-Formal Language for Auditable AI Planning
AI总结：
NormCode是一种半形式语言，通过强制数据隔离和严格区分语义与语法操作，实现AI工作流的可审计性，确保透明性和可验证性。
摘要：
随着AI系统进入法律推理、医疗诊断和金融决策等高风险领域，监管者和从业者对可审计性的需求日益增加。可审计性意味着能够精确追溯多步骤工作流中每一步所见和所做。当前基于大语言模型的工作流本质上是不透明的。上下文污染，定义为在推理步骤中信息的积累，导致模型产生幻觉并失去对约束的跟踪。同时，隐含的数据流使得无法重建任何给定步骤实际上接收的输入。我们提出了NormCode，一种半形式语言，通过构建使AI工作流可审计。每个推理步骤在强制的数据隔离下运行，并且只能访问显式传递的输入。这消除了跨步骤污染，确保每个中间状态都可以检查。严格区分语义操作（即概率性语言模型推理）和语法操作（即确定性数据流）允许审计员清晰地区分推理与机械重构。由NCDS、NCD、NCN和NCDN文件组成的多格式生态系统，使开发者、领域专家和审计员能够以适合他们个人需求的格式检查同一计划。四阶段编译流水线将自然语言意图转换为可执行的JSON存储库。一个视觉Canvas应用程序提供实时图可视化和断点调试。我们通过在基础X加法上实现完全准确性和通过自行托管执行NormCode编译器本身来验证该方法。这些结果证明了结构化中间表示可以弥合人类直觉和机器严谨性，同时保持完全透明。
英文摘要：
As AI systems move into high stakes domains such as legal reasoning, medical diagnosis, and financial decision making, regulators and practitioners increasingly demand auditability. Auditability means the ability to trace exactly what each step in a multi step workflow saw and did. Current large language model based workflows are fundamentally opaque. Context pollution, defined as the accumulation of information across reasoning steps, causes models to hallucinate and lose track of constraints. At the same time, implicit data flow makes it impossible to reconstruct what any given step actually received as input. We present NormCode, a semi formal language that makes AI workflows auditable by construction. Each inference step operates in enforced data isolation and can access only explicitly passed inputs. This eliminates cross step contamination and ensures that every intermediate state can be inspected. A strict separation between semantic operations, meaning probabilistic language model reasoning, and syntactic operations, meaning deterministic data flow, allows auditors to clearly distinguish inference from mechanical restructuring. The multi format ecosystem, consisting of NCDS, NCD, NCN, and NCDN files, allows developers, domain experts, and auditors to inspect the same plan in formats suited to their individual needs. A four phase compilation pipeline transforms natural language intent into executable JSON repositories. A visual Canvas application provides real time graph visualization and breakpoint debugging. We validate the approach by achieving full accuracy on base X addition and by self hosted execution of the NormCode compiler itself. These results demonstrate that structured intermediate representations can bridge human intuition and machine rigor while maintaining full transparency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
