发现法律条文共引关系随时间显著失效，尤其民事领域衰退明显。
Temporal Decay of Co-Citation Predictability: A 20-Year Statute Retrieval Benchmark from 396M Ukrainian Court Citations
- 构建20年跨时序的乌克兰判例引用基准，分析共引可预测性变化
- 民事法律共引预测能力下降57%（0.35→0.15），刑事程序保持稳定
- 中频法条（1K-10K次引用）预测力折半，适合法律检索系统优化者阅读
共引结构被广泛认为在法律信息系统中具有稳定检索信号。我们通过构建涵盖2007至2026年共20个年度快照、3.96亿条乌克兰法典引用的基准数据集UA-StatuteRetrieval，对这一假设进行纵向验证。基于全双部引用图的留一法协议，发现Adamic-Adar MRR在固定文章集上下降33%（0.43→0.29），在训练/测试时间分割下下降47%（0.51→0.27），确认真实的时间衰减而非组成变化或评估伪影。衰减非均匀：刑事程序保持稳定（MRR≈0.40），而民事法从0.35降至0.15，与2017年司法改革同步。高引用核心条文（>10万次）抗衰减，但中频条文（1K-10K次）预测力损失一半。文本基线BM25衰减更快（31%），嵌入漂移分析显示E5-large揭示引用语义发生4.3%变化，提供机制解释。基准已发布于https://huggingface.co/datasets/overthelex/ua-statute-retrieval。
原文摘要 · Abstract (English)
Co-citation structure is widely assumed to provide stable retrieval signal in legal information systems. We test this assumption longitudinally by constructing UA-StatuteRetrieval, a benchmark that measures co-citation predictability across 20 annual snapshots (2007-2026) of 396 million codex citations from 101 million Ukrainian court decisions. Using a leave-one-out protocol over the full bipartite citation graph, we find that Adamic-Adar MRR declines 33% on a fixed set of articles (from 0.43 to 0.29) and 47% under a train/test temporal split (from 0.51 to 0.27) confirming genuine temporal decay rather than compositional shift or evaluation artifact. The decay is non-uniform: criminal procedure maintains stable co-citation patterns (MRR ~0.40), while civil law degrades from 0.35 to 0.15, coinciding with the 2017 judicial reform. Hub articles (>100K citations) resist decay, but mid-frequency articles (1K-10K) -- the practical retrieval frontier lose half their predictability. A BM25 text baseline decays even faster (31%), and embedding drift analysis with E5-large reveals a 4.3% semantic shift in how articles are cited, providing a mechanistic explanation for the observed decay. The benchmark is released at https://huggingface.co/datasets/overthelex/ua-statute-retrieval.
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。