用证据定位方法提升施工文档审查准确率，发现局部细节与整体范围需权衡。
Evidence-Grounded Constraint Checking in Construction Documents
- 基于文本、几何与修订关系构建可追溯的规则检查流程
- 调整图像分配策略使项目族平均准确率提升10.6个百分点
- 适合需要高精度审查的工程文档自动化系统开发者
专业文档审查是一个依赖文本、几何、页面和修订关系的约束检查问题。本文提出一种证据锚定的处理流程：对提取事实进行标准化，以四状态规则确定性执行，保留原始文本片段，并对未解决案例进行升级处理。在29个建筑项目的160项参考任务上评估其PDF证据分配器，采用重复四系统测试与不重叠双系统广度扩展。重复测试中，将四张图像预算从检索页概览重新分配为一张概览加三张重叠区块，使项目族标准化决策准确率提升10.6个百分点（95%项目簇自助置信区间：4.3至18.0；精确p=0.031）。此效果在更广范围测试中未持续：Region-RAG使准确率下降4.1点（95%置信区间：-10.2至1.9；精确p=0.209），而等量图像下更侧重页面广度。精确发现集恢复率仍低，误通过现象普遍，重复运行一致性校准不足。结果揭示分辨率与覆盖范围之间的权衡，而非区域聚焦证据的普遍优势，推动规则感知的证据路由与专家审查结合。
原文摘要 · Abstract (English)
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.
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。