arXiv 建筑语义标准论文· Humza Akhtar·· 12 小时前次级推荐AI 评分75
「英中对照」arXiv论文提出AI元数据可争议治理方法，以HVAC用例演示
Contestable Agents for Data Governance: Recording Human Stewardship of AI-Generated Metadata Across Structured and Unstructured Systems
AI 导读
2026年10月22日提交的arXiv论文提出“可争议治理”方法：大语言模型代理为有争议的元数据决策生成带评分和引用的论据，人工监管员在提交前可接受、拒绝、修改或补充论据，治理记录留存证据、干预与结果。
推荐理由
该文把LLM代理引入建筑元数据治理，以Brick Schema点位分类等HVAC用例演示人工留痕审核流程，对楼控与数据治理团队的AI采用决策有参考价值；但目前仅为arXiv预印本的方法描述与示例，效果与落地情况未经独立验证，其开源参考实现可作为核验入口。
正文 · 中英逐段对照
View PDF HTML (experimental)查看 PDF HTML（实验性）
Abstract:Industrial organizations hold operational knowledge in structured records, such as telemetry, point lists, and transactions, and in unstructured sources, such as manuals, service notes, communications, and inspection reports. Governance programs often manage these sources separately. Classifying, linking, and documenting them depends on a small group of employees with deep domain knowledge. Agents built on large language models can propose metadata, cite documents, and flag quality issues, but unreviewed proposals can spread errors into downstream systems. A perfunctory approval leaves no record of what a reviewer checked. We present contestable governance: specialist agents produce scored, cited arguments for disputed metadata decisions; a steward can accept, reject, modify, or add arguments before commit; and a governance record retains the evidence, interventions, and outcome. A versioned domain glossary supplies model-specific terms and acronym definitions to the agents. We describe the workflow, a triage path that reserves full argumentation for uncertain proposals while preserving review before commit, the scoring and record models, and a gate that controls which verified decisions become precedent. Two HVAC use cases illustrate the pattern: point classification using Brick Schema class labels, supported by an open reference implementation, and an illustrative warranty failure-mode decision linking claim fields and telemetry to service notes and revisioned bulletins. 摘要：工业组织将运营知识保存在结构化记录（如遥测数据、点位清单和交易记录）以及非结构化来源（如手册、服务记录、通信和巡检报告）中。治理项目通常分别管理这些来源。对它们进行分类、关联和记录依赖于少数具有深厚领域知识的员工。基于大语言模型构建的智能体可以提出元数据建议、引用文档并标记质量问题，但未经审查的建议可能会将错误传播到下游系统。流于形式的批准不会留下审查者究竟检查了哪些内容的记录。我们提出了可争辩治理（contestable governance）：专业智能体针对有争议的元数据决策生成带有评分和引用的论据；管理员（steward）可以在提交前接受、拒绝、修改或添加论据；治理记录则保留证据、干预措施和结果。一个版本化的领域词汇表为智能体提供特定于模型的术语和缩写词定义。我们描述了该工作流程、一条分诊路径——将完整的论证过程保留给不确定的建议，同时在提交前保留审查环节——以及评分与记录模型，还有一个控制哪些经过验证的决策成为先例的门控机制。两个 HVAC 用例说明了这一模式：基于 Brick Schema 类标签的点位分类（由一个开源参考实现支持），以及一个说明性的保修故障模式决策，将索赔字段和遥测数据与服务记录及版本化公告相关联。
| Comments:备注： | 15 pages, 2 figures, 2 tables15 页，2 幅图，2 个表格 |
| Subjects:学科分类： | Artificial Intelligence (cs.AI); Databases (cs.DB); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)人工智能 (cs.AI)；数据库 (cs.DB)；人机交互 (cs.HC)；多智能体系统 (cs.MA) |
| Cite as:引用格式： | arXiv:2610.31553 [cs.AI] |
| (or arXiv:2610.31553v1 [cs.AI] for this version) （或 arXiv:2610.31553v1 [cs.AI]，对应此版本） | |
| https://doi.org/10.48550/arXiv.2610.31553 arXiv-issued DOI via DataCite (pending registration) arXiv 通过 DataCite 颁发的 DOI（待注册） |
Submission history提交历史
From: Brian Freeman [view email]
[v1]
Thu, 22 Oct 2026 16:57:01 UTC (439 KB)
来自：Brian Freeman [查看邮箱]
[v1]
2026 年 10 月 22 日（周四）16:57:01 UTC（439 KB）
来源：arXiv 建筑语义标准论文 · arxiv.org