GVD: Governed Versioning and Deduplication for Document Repositories

GVD：文档存储库的受控版本控制与去重

Abstract: Document repositories evolve continuously. Guidelines and policies are revised, superseded, and re-uploaded, so the same content recurs in different wording and newer versions refine or contradict earlier ones. These inconsistencies belong to the growing collection rather than to any single document, yet existing work treats versioning, duplicate detection, and contradiction detection as isolated pairwise tasks and stops once a pair is labeled.

摘要： 文档存储库在不断演变。指南和政策会被修订、取代并重新上传，导致相同的内容以不同的措辞反复出现，且新版本往往会对旧版本进行细化或产生矛盾。这些不一致性存在于不断增长的文档集合中，而非单一文档内。然而，现有的研究将版本控制、重复检测和矛盾检测视为孤立的成对任务，且在标记出一对关系后便停止处理。

We present GVD (Governed Versioning and Deduplication), a framework that unifies cross-document version linking with rule-level conflict resolution under an auditable update policy. Incoming documents are assigned to version families through bidirectional rule alignment, and their rules are compared against the family memory to identify duplicates, contradictions, asymmetric refinements, and new knowledge, with Counterfactual Span Probing (CSP) resolving related pairs that inference misclassifies as neutral.

我们提出了 GVD（受控版本控制与去重），这是一个在可审计更新策略下，将跨文档版本链接与规则级冲突解决统一起来的框架。传入的文档通过双向规则对齐被分配到各个版本族中，其规则会与族内存进行比对，以识别重复项、矛盾项、非对称细化项和新知识。此外，反事实跨度探测（CSP）技术被用于解决那些被推理模型误分类为“中性”的相关文档对。

Relation-specific policies suppress duplicates and escalate only consequential changes for review, retaining version lineage as an audit trail. The pipeline runs fully locally, with no large language model. On 120 enterprise documents processed as 140 ingestions across 59 version families, GVD reaches an F1 of 0.97 for version-family construction and 0.94 for rule-level consistency, with CSP raising rule consistency from 0.90 to 0.94.

基于关系的策略会抑制重复内容，仅将重要的变更升级以供审查，并保留版本谱系作为审计追踪。该流水线完全在本地运行，无需使用大型语言模型。在处理 120 份企业文档（共 140 次摄入，分布在 59 个版本族中）的测试中，GVD 在版本族构建任务上达到了 0.97 的 F1 分数，在规则级一致性上达到了 0.94，其中 CSP 技术将规则一致性从 0.90 提升到了 0.94。