{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OD6XR6IZGFQ6AL7O6K23MBDMUL","short_pith_number":"pith:OD6XR6IZ","schema_version":"1.0","canonical_sha256":"70fd78f9193161e02feef2b5b6046ca2c239dbac6abee359f344b226f6fdd8ff","source":{"kind":"arxiv","id":"2503.00402","version":2},"attestation_state":"computed","paper":{"title":"A Topology-Aware Localized Update Strategy for Graph-Based ANN Index","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ge Yu, Guoliang Li, Ji Sun, Ruicheng Liu, Shengyuan Lin, Shufeng Gong, Song Yu, Yanfeng Zhang, Yijie Zhou, Yongqing Xie","submitted_at":"2025-03-01T08:33:43Z","abstract_excerpt":"The graph-based index has been widely adopted to meet the demand for approximate nearest neighbor search (ANNS) for high-dimensional vectors. However, in dynamic scenarios involving frequent vector insertions and deletions, existing systems improve update throughput by adopting a batch update method. However, a large batch size leads to significant degradation in search accuracy.\n  This work aims to improve the performance of graph-based ANNS systems in small-batch update scenarios, while maintaining high search efficiency and accuracy. We identify two key issues in existing batch update syste"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.00402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-03-01T08:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"d9ce1783037b383b0749823f9db2e955a91cd436cd8e15179867c1e2269aee3d","abstract_canon_sha256":"2a718afb03907a610f5717b77f2726d8851f12497dd63a29f64872905a741be6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:46.169720Z","signature_b64":"6LRJoz39tNwQg3YZ8wY+LJQriQddygBLRy27RYG1Zq5Ncg2SsmUAL3g6dv2ku03iHUMkFkI1EGaAy8OsV0dkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70fd78f9193161e02feef2b5b6046ca2c239dbac6abee359f344b226f6fdd8ff","last_reissued_at":"2026-07-05T10:33:46.168639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:46.168639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Topology-Aware Localized Update Strategy for Graph-Based ANN Index","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ge Yu, Guoliang Li, Ji Sun, Ruicheng Liu, Shengyuan Lin, Shufeng Gong, Song Yu, Yanfeng Zhang, Yijie Zhou, Yongqing Xie","submitted_at":"2025-03-01T08:33:43Z","abstract_excerpt":"The graph-based index has been widely adopted to meet the demand for approximate nearest neighbor search (ANNS) for high-dimensional vectors. However, in dynamic scenarios involving frequent vector insertions and deletions, existing systems improve update throughput by adopting a batch update method. However, a large batch size leads to significant degradation in search accuracy.\n  This work aims to improve the performance of graph-based ANNS systems in small-batch update scenarios, while maintaining high search efficiency and accuracy. We identify two key issues in existing batch update syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00402","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.00402/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.00402","created_at":"2026-07-05T10:33:46.168777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00402v2","created_at":"2026-07-05T10:33:46.168777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00402","created_at":"2026-07-05T10:33:46.168777+00:00"},{"alias_kind":"pith_short_12","alias_value":"OD6XR6IZGFQ6","created_at":"2026-07-05T10:33:46.168777+00:00"},{"alias_kind":"pith_short_16","alias_value":"OD6XR6IZGFQ6AL7O","created_at":"2026-07-05T10:33:46.168777+00:00"},{"alias_kind":"pith_short_8","alias_value":"OD6XR6IZ","created_at":"2026-07-05T10:33:46.168777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00728","citing_title":"When to Repair a Graph ANN Index: Navigability-Signal-Triggered Local Repair Protects Tail Recall Under Bursty Churn","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26474","citing_title":"Generalized Range Filtering Approximate Nearest Neighbor Search: Containment and Overlap [Technical Report]","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL","json":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL.json","graph_json":"https://pith.science/api/pith-number/OD6XR6IZGFQ6AL7O6K23MBDMUL/graph.json","events_json":"https://pith.science/api/pith-number/OD6XR6IZGFQ6AL7O6K23MBDMUL/events.json","paper":"https://pith.science/paper/OD6XR6IZ"},"agent_actions":{"view_html":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL","download_json":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL.json","view_paper":"https://pith.science/paper/OD6XR6IZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00402&json=true","fetch_graph":"https://pith.science/api/pith-number/OD6XR6IZGFQ6AL7O6K23MBDMUL/graph.json","fetch_events":"https://pith.science/api/pith-number/OD6XR6IZGFQ6AL7O6K23MBDMUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL/action/storage_attestation","attest_author":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL/action/author_attestation","sign_citation":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL/action/citation_signature","submit_replication":"https://pith.science/pith/OD6XR6IZGFQ6AL7O6K23MBDMUL/action/replication_record"}},"created_at":"2026-07-05T10:33:46.168777+00:00","updated_at":"2026-07-05T10:33:46.168777+00:00"}