{"ID":2900974,"CreatedAt":"2026-06-01T05:51:17.9442275Z","UpdatedAt":"2026-06-01T09:30:02.809313052Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2605.31100","arxiv_id":"2605.31100","title":"Vector Linking via Cross-Model Local Isometric Consistency","abstract":"We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model object correspondences using only vectors. Empirically and theoretically, we show that independently trained contrastive encoders exhibit local geometric consistency: short-range distances are approximately preserved up to a scale factor, while long-range distances are not due to model-specific distortion. Building on this, we propose an iterative, reference-based geometric embedding hashing that recovers vector links from a tiny seed set of paired anchors. It represents each vector by distances to sampled paired anchors, proposes candidate links via hash-space matching, and aggregates evidence across views in a Beta-Bernoulli posterior to bootstrap high-confidence links as new anchors. Experiments across multiple benchmarks and embedding model pairs demonstrate accurate and robust linking under varying overlap, seed budgets, and out-of-domain anchors, with applications to vector database integration and cross-model clustering. Code is available at https://github.com/DBgroup-Edinburgh/VecLinking.","short_abstract":"We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model object correspondences using only vectors. Empirically and theoretically, we show that independently trained contrastive encoders exhibit local geometric consistency: sho...","url_abs":"https://arxiv.org/abs/2605.31100","url_pdf":"https://arxiv.org/pdf/2605.31100v1","authors":"[\"Ziying Chen\",\"Yang Cao\",\"He Sun\",\"Beining Yang\",\"Tianjian Yang\"]","published":"2026-05-29T10:12:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.DB\",\"cs.IR\"]","methods":"[]","has_code":false,"code_links":[{"ID":612548,"CreatedAt":"2026-06-01T05:51:17.9442275Z","UpdatedAt":"2026-06-01T05:51:17.9442275Z","DeletedAt":null,"paper_id":2900974,"paper_url":"https://arxiv.org/abs/2605.31100","paper_title":"Vector Linking via Cross-Model Local Isometric Consistency","repo_url":"https://github.com/DBgroup-Edinburgh/VecLinking","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}