发表机构
JudicialMind（司法思维机构）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对机器解析法规存在分歧的问题，为机器提取法律逻辑的Duquenne-Guigues蕴含基构建生存性证明，在两类法规数据集上验证了其可用性，同时揭示其脆弱性并发布相关资源。
AI 中文摘要
法规在人们阅读前越来越多地被机器解析，但解析器存在分歧：针对密苏里州法规，两个独立编写的提取器在数值阈值存在性上的假阴性率分歧为0.43。我们探究何种形式逻辑能在这类噪声中留存。我们为机器提取的法规语境的Duquenne-Guigues蕴含基构建被动生存性证明：测量每个属性的提取器间分歧，在1000次蒙特卡洛试验中回放至该基，仅当蕴含的单侧Wilson 95%生存下界达到0.95时才对其进行认证；每项认证的蕴含均附带前提区间和最小反例。在29365个密苏里条款和502个印度中央法案条款上，预注册的保留门通过验证（7个标题中的10个法规族完全通过；11个中的16个在5%容差下通过），但在一种全局部署的误差模型下，93.2%的保留章节低于信息性下限，2×2析因分析将此归因于校准率转移而非选择。该证明可用但脆弱：需按章节校准或采用容错方式部署。代码、数据产品及审计轨迹（含一项撤回声明）已发布。
英文摘要
Statutes are increasingly parsed by machines before people read them, and the parsers disagree: on Missouri's statutes, two independently written extractors diverge on numeric-threshold presence at a false-negative rate of 0.43. We ask what formal logic survives such noise. We build a passive survival certificate for the Duquenne-Guigues implication basis of machine-extracted statutory contexts: per-attribute inter-extractor disagreement is measured, replayed against the basis in 1,000 Monte Carlo trials, and an implication is certified only when a one-sided Wilson 95% lower bound on survival reaches 0.95; every certified implication carries premise spans and a minimal counterexample. On 29,365 Missouri sections and 502 Indian central-Act sections, the preregistered held-out gate passes (10 statute families across 7 Titles exact; 16 across 11 with 5% tolerance), yet under one globally deployed error model 93.2% of held-out chapters fall below the informativeness floor, and a 2x2 factorial assigns that to calibration-rate transfer, not selection. The certificate is usable but fragile: deploy it per-chapter-calibrated or error-tolerant. Code, data products, and the audit trail, including one retracted claim, are released.
Comments18 pages, 9 figures, 13 tables (6 main text, 7 appendix). Code, data products, and preregistration to be released on GitHub
