ai.hackcv
论文精选 80arXiv

Evidence-Grounded Constraint Checking in Construction Documents· 施工文档中基于证据的约束检查

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

领域:cs.AI作者:Rashid Mushkani、Hugo Berard、Shin Koseki
相关推荐

本站内容由 LLM 精选聚合,原文版权归 arXiv 所有 · 摘录仅供参考