Two-hop QA retrieval splits queries into two regimes determined by whether the hop-2 entity is explicitly named in the question (Q-dominant) or only in the bridge passage (B-dominant). We formalize this split with three theorems: (T1) per-query AUC is a monotone function of the cosine separation margin, with R^2 >= 0.90 for six of eight type-encoder pairs; (T2) regime is characterized by two surface-text predicates, with P1 decisive for routing and P2 qualifying the B-dominant case, holding across three encoders and three datasets; and (T3) bridge advantage requires the relation-bearing sentence, not entity name alone, with removal causing an 8.6-14.1 pp performance drop (p < 0.001). Building on this theory, we propose RegimeRouter, a lightweight binary router that selects between question-only and question-plus-relation-sentence retrieval using five text features derived directly from the predicate definitions. Trained on 2WikiMultiHopQA (n = 881, 5-fold cross-fitted) and applied zero-shot to MuSiQue and HotpotQA, RegimeRouter achieves +5.6 pp (p < 0.001), +5.3 pp (p = 0.002), and +1.1 pp (non-significant, no-regret) R@5 improvement, respectively, with artifact-driven.

翻译：双跳问答检索将查询划分为两种模式，分别取决于跳2实体在问题中被明确提及（Q主导型）还是仅在桥接段落中出现（B主导型）。我们通过三个定理形式化这一划分：(T1) 逐查询AUC是余弦间隔分离度的单调函数，在八个编码器-类型组合中有六个的R²≥0.90；(T2) 模式可通过两个表层文本谓词表征，其中P1决定路由选择，P2限定B主导情形，该结论在三种编码器和三个数据集上保持成立；(T3) 桥接优势需要包含关系承载句而非仅实体名称，移除该句将导致性能下降8.6-14.1个百分点（p<0.001）。基于该理论，我们提出轻量级二值路由器RegimeRouter，它利用从谓词定义直接推导的五种文本特征，在仅问题检索与问题加关系句检索之间进行选择。该模型在2WikiMultiHopQA（n=881，5折交叉拟合）上训练，零样本迁移至MuSiQue和HotpotQA后，分别实现R@5提升+5.6个百分点（p<0.001）、+5.3个百分点（p=0.002）和+1.1个百分点（无统计显著性，无遗憾提升），且具有可解释性。