发表机构
The Engineering and Technology College, Chengdu University of Technology, Leshan, China; School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia; Department of Art and Design, The Engineering and Technology College, Chengdu University of Technology, Leshan, China（成都理工大学工程技术学院; 马来西亚理科大学计算机科学学院; 成都理工大学工程技术学院艺术设计系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究法律先例检索中引用上下文评估的时间泄漏问题，提出时间接纳分解方法，通过在两个司法管辖区进行可控审计，添加零训练锚定通道，量化泄漏程度，提升检索效果，在零训练时达到较好的R@1000估计值。
AI 中文摘要
传入的引用上下文（即后来的案例在引用某个案例时所描述的文本）是法律先例检索的有力信号，但目前在评估时没有时间围栏：在查询时，目标先例尚未被未来案例引用，因此无围栏方法会将部署时尚未获得的证据归功于自身。我们的核心贡献是衡量其程度：一种时间接纳分解方法，将天真的放宽围栏增益分解为真正的未来引用泄漏、合法的查询前接纳和索引效应，并报告幻影分数（即未来证据的份额）。我们将其实例化为对两个司法管辖区（美国联邦的CLERC，184万份文档；欧洲人权法院的ECtHR-PCR）的传入引用检索进行可控的可部署性审计，添加了一个仅接纳查询日期之前引用者的零训练锚定通道。在ECtHR-PCR上，天真增益中只有14.9%是真正的未来证据；在CLERC上，随着围栏放宽，过度信用增长到+4.95 R@1000。在围栏之下，零训练通道在CLERC上比BM25的R@1000增益+16.1，清除了引用程度控制，并在零训练时达到了与ECtHR-PCR上最强训练系统相似的已发表R@1000估计值（79.56对79.39）。
英文摘要
Prior case retrieval (PCR) aims to identify the precedent cases relevant to the facts of a query case. Incoming citation context, the text with which later cases characterize a case when citing it, is a powerful relevance signal, yet it is typically evaluated without a temporal constraint, so the retriever is credited with citations made after the query. We introduce a temporally fenced retriever with no learned parameters that augments BM25 with incoming citation context restricted to citations predating the query, together with a temporal-admission decomposition that quantifies the phantom fraction: the share of a citation-context gain attributable to citations not known to predate the query. Experiments span two jurisdictions, U.S. federal (CLERC) and European (ECtHR-PCR) case law. On ECtHR-PCR, without any training, the fenced retriever outperforms a strong degree-controlled baseline across the full recall ladder, and a temporal-admission decomposition attributes 14.9% (validation) of an unfenced citation-context gain over BM25 to citations not known to predate the query. Citation-context retrieval must therefore be temporally fenced and degree-controlled before its reported gains can be interpreted.
