In any domain where knowledge accumulates under formal authority -- law, drug regulation, software security -- a later document can formally void an earlier one while remaining semantically distant from it. We formalize this as Controlling Authority Retrieval (CAR): recovering the active frontier front(cl(A_k(q))) of the authority closure of the semantic anchor set -- a different mathematical problem from argmax_d s(q,d). The two central results are: Theorem 4 (CAR-Correctness Characterization) gives necessary-and-sufficient conditions on any retrieved set R for TCA(R,q)=1 -- frontier inclusion and no-ignored-superseder -- independent of how R was produced. Proposition 2 (Scope Identifiability Upper Bound) establishes phi(q) as a hard worst-case ceiling: for any scope-indexed algorithm, TCA@k <= phi(q) * R_anchor(q), proved by an adversarial permutation argument. Three independent real-world corpora validate the proved structure: security advisories (Dense TCA@5=0.270, two-stage 0.975), SCOTUS overruling pairs (Dense=0.172, two-stage 0.926), FDA drug records (Dense=0.064, two-stage 0.774). A GPT-4o-mini experiment shows the downstream cost: Dense RAG produces explicit "not patched" claims for 39% of queries where a patch exists; Two-Stage cuts this to 16%. Four benchmark datasets, domain adapters, and a single-command scorer are released at https://github.com/andremir/car-retrieval.

翻译：在受正式权威约束的知识积累领域——法律、药品监管、软件安全——后期发布的文档可以正式废止较早的文档，同时与之保持语义上的疏离。我们将此形式化为控制性权威检索（CAR）：恢复语义锚点集的权威闭包中的有效前沿front(cl(A_k(q)))——这是与argmax_d s(q,d)不同的数学问题。两个核心结果是：定理4（CAR-正确性刻画）给出了对任意检索集R满足TCA(R,q)=1的充要条件——前沿包含性且无忽略的取代者——与R的生成方式无关。命题2（范围可辨识性上界）将phi(q)确立为硬性最差情况上限：对于任何基于范围索引的算法，TCA@k ≤ phi(q) * R_anchor(q)，通过对抗性排列论证证明。三个独立真实语料库验证了该结构：安全公告（密集检索TCA@5=0.270，两阶段检索0.975）、美国最高法院推翻判决对（密集检索=0.172，两阶段检索0.926）、FDA药品记录（密集检索=0.064，两阶段检索0.774）。GPT-4o-mini实验展示了下游成本：密集RAG在39%存在补丁的查询中产生明确"未修补"声明；两阶段方法将此比例降至16%。四个基准数据集、领域适配器及单命令评分器已在https://github.com/andremir/car-retrieval发布。