建筑文档中基于证据的约束检查
Evidence-Grounded Constraint Checking in Construction Documents
浏览论文内容
中文总结 AI 辅助
该研究针对建筑文档审查的约束检查问题，提出基于证据的流程，通过实验发现调整图像预算分配可提升项目家族决策准确性，同时揭示分辨率广度权衡，为证据路由和专家审查提供依据。
中文摘要 AI 辅助
专业文档审查是一个约束检查问题，其决策依赖于文本、几何、页面和文档修订之间的关系。我们提出了一种基于证据的流程，该流程对提取的事实进行标准化，确定性执行四态规则，保留源文本跨度，并升级未解决的案例。我们使用重复四系统测试和不相交两系统广度扩展，在来自29个建筑项目的160个基于参考的任务上评估其PDF证据分配器。在重复测试中，将四张图像预算从检索到的页面概览重新分配到一个概览和三个重叠的图块，使项目家族标准化决策准确性提高了10.6个百分点（95%项目集群自助置信区间：4.3至18.0；精确p值=0.031）。该效果在更广泛的区块中不持续：Region-RAG使准确性变化-4.1个百分点（95%置信区间：-10.2至1.9；精确p值=0.209），而等图像敏感性有利于页面广度。精确发现集恢复率仍然较低，误判仍然常见，重复运行的一致性校准较差。结果确定了分辨率广度权衡，而非以区域为重点的证据的普遍优势，为规则感知的证据路由和专家审查提供了动力。
英文摘要
Professional-document review is a constraint-checking problem in which decisions depend on relations among text, geometry, pages, and document revisions. We present an evidence-grounded pipeline that normalizes extracted facts, executes four-state rules deterministically, retains source spans, and escalates unresolved cases. We evaluate its PDF evidence allocator on 160 reference-based tasks from 29 construction projects using a repeated four-system test and a disjoint two-system breadth extension. In the repeated test, reallocating a four-image budget from retrieved page overviews to one overview and three overlapping tiles improves project-family standardized decision accuracy by 10.6 percentage points (95% project-cluster bootstrap CI: 4.3 to 18.0; exact p = 0.031). This effect does not persist in the broader block: Region-RAG changes accuracy by -4.1 points (95% CI: -10.2 to 1.9; exact p = 0.209), while an equal-image sensitivity favors page breadth. Exact finding-set recovery remains low, false passes remain common, and repeated-run agreement is poorly calibrated. The results identify a resolution-breadth trade-off rather than a universal advantage for region-focused evidence, motivating rule-aware evidence routing and expert review.
