Approximate nearest neighbor (ANN) graph indices such as HNSW and Vamana construct their edge topology in full-precision or high-fidelity quantized metric spaces, relegating binary quantization (BQ) to a post-hoc distance estimator during search. This paper asks a different question: Can binary quantization define the graph topology itself -- and if so, under what conditions? We study this question through QuIVer (Quantized Index for Vector Retrieval), a training-free ANN graph index that performs Vamana edge selection, diversity pruning, and beam-search navigation entirely within a 2-bit Sign-Magnitude BQ metric space, accessing float32 vectors only for final reranking. Systematic evaluation on twelve million-scale datasets reveals a sharp applicability boundary: BQ-native topology is highly effective on cosine-native contrastive-learning embeddings (>=88% Recall@10 at ef=64 across five datasets, 384--3072 dimensions), moderately effective on multimodal CLIP data (71--78%), and empirically unsuitable for Euclidean-native or structureless distributions (<15%). Our results suggest an empirical "impossible triangle" between aggressive compression, high throughput, and universal data compatibility. The central contribution is not merely the system, but the boundary it reveals: falsifiable criteria for when industrial vector search systems can safely trade metric fidelity for compact BQ-native navigation. On compatible workloads, the system benefits are substantial: QuIVer's BQ-native hot path (<1.3 GB for 1M vectors) yields 2.5--5.5x higher multi-threaded throughput than DiskANN Rust and HNSW variants at matched recall, with 4.7x less hot memory and no codebook or rotation training (unlike PQ/OPQ/RaBitQ).

翻译：近似最近邻（ANN）图索引（如HNSW和Vamana）在全精度或高保真量化度量空间中构建其边拓扑，而将二值量化（BQ）仅作为搜索过程中的事后距离估计器。本文提出一个不同的问题：二值量化能否自主定义图拓扑——如果可行，又在何种条件下成立？我们通过QuIVer（面向向量检索的量化索引）研究该问题，这是一种免训练的ANN图索引，它完全在2比特符号-幅值BQ度量空间内执行Vamana边选择、多样性剪枝和波束搜索导航，仅针对最终重排序访问float32向量。在十二个百万级数据集上的系统评估揭示了一个清晰的适用边界：BQ原生拓扑在余弦原生对比学习嵌入上高度有效（在ef=64条件下，五个维度384-3072的数据集上Recall@10>=88%），在多模态CLIP数据上中等有效（71-78%），而在欧氏原生或无结构分布上经验上不适用（<15%）。我们的结果暗示了一种在激进压缩、高吞吐量和通用数据兼容性之间存在的经验性“不可能三角”。本文的核心贡献不仅是该系统，更是其揭示的边界：可证伪的条件，用以判断工业级向量搜索系统何时可以安全地用度量保真度换取紧凑的BQ原生导航。在兼容的工作负载上，该系统效益显著：QuIVer的BQ原生热路径（100万向量占用<1.3 GB）在匹配召回率下，相比DiskANN Rust和HNSW变体实现了2.5-5.5倍的多线程吞吐量提升，热内存减少4.7倍，且无需码本或旋转训练（不同于PQ/OPQ/RaBitQ）。