{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HLGOUZYU4TBFFZJIPTSXRWXBGR","short_pith_number":"pith:HLGOUZYU","schema_version":"1.0","canonical_sha256":"3accea6714e4c252e5287ce578dae13450e0f02256e3e6db6f4ead20e3810509","source":{"kind":"arxiv","id":"2502.13826","version":1},"attestation_state":"computed","paper":{"title":"In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Badrish Chandramouli, Haike Xu, Harsha Vardhan Simhadri, Magdalen Dobson Manohar, Philip A. Bernstein, Richard Wen","submitted_at":"2025-02-19T15:41:08Z","abstract_excerpt":"Indices for approximate nearest neighbor search (ANNS) are a basic component for information retrieval and widely used in database, search, recommendation and RAG systems. In these scenarios, documents or other objects are inserted into and deleted from the working set at a high rate, requiring a stream of updates to the vector index. Algorithms based on proximity graph indices are the most efficient indices for ANNS, winning many benchmark competitions. However, it is challenging to update such graph index at a high rate, while supporting stable recall after many updates. Since the graph is s"},"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":"2502.13826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-19T15:41:08Z","cross_cats_sorted":[],"title_canon_sha256":"22a57d11b184eb91e1fc050cc652749b59e37bb981050d69faf7b66fc05cfcd9","abstract_canon_sha256":"1e9167ad41eadce3fbaa0d6d6f2500bd72cf81931647c1fd0d9aed695a350c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:01.025167Z","signature_b64":"6G8f+PCiCjyL6PJI3UzajYU9J92uER5tbirnGX0B0DviCpuQ5WdVO4ThJ2d99LiwsPkZ0Lrlb9fR3S5DNK4XBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3accea6714e4c252e5287ce578dae13450e0f02256e3e6db6f4ead20e3810509","last_reissued_at":"2026-07-05T10:17:01.024714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:01.024714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Badrish Chandramouli, Haike Xu, Harsha Vardhan Simhadri, Magdalen Dobson Manohar, Philip A. Bernstein, Richard Wen","submitted_at":"2025-02-19T15:41:08Z","abstract_excerpt":"Indices for approximate nearest neighbor search (ANNS) are a basic component for information retrieval and widely used in database, search, recommendation and RAG systems. In these scenarios, documents or other objects are inserted into and deleted from the working set at a high rate, requiring a stream of updates to the vector index. Algorithms based on proximity graph indices are the most efficient indices for ANNS, winning many benchmark competitions. However, it is challenging to update such graph index at a high rate, while supporting stable recall after many updates. Since the graph is s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13826","kind":"arxiv","version":1},"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/2502.13826/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":"2502.13826","created_at":"2026-07-05T10:17:01.024770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13826v1","created_at":"2026-07-05T10:17:01.024770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13826","created_at":"2026-07-05T10:17:01.024770+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLGOUZYU4TBF","created_at":"2026-07-05T10:17:01.024770+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLGOUZYU4TBFFZJI","created_at":"2026-07-05T10:17:01.024770+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLGOUZYU","created_at":"2026-07-05T10:17:01.024770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02992","citing_title":"Slipstream: Locality-Aware Graph Index Construction for Streaming Approximate Nearest Neighbor Search","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19335","citing_title":"Leveraging I/O Stalls for Efficient Scheduling in ANNS","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09173","citing_title":"Decoupling Vector Data and Index Storage for Space Efficiency","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25401","citing_title":"DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09331","citing_title":"Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11523","citing_title":"NAVIS: Concurrent Search and Update with Low Position-Seeking Overhead in On-SSD Graph-Based Vector Search","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10135","citing_title":"ScaleGANN: Accelerate Large-Scale ANN Indexing by Cost-effective Cloud GPUs","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09173","citing_title":"Decoupling Vector Data and Index Storage for Space Efficiency","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20401","citing_title":"Onyx: Cost-Efficient Disk-Oblivious ANN Search","ref_index":131,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR","json":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR.json","graph_json":"https://pith.science/api/pith-number/HLGOUZYU4TBFFZJIPTSXRWXBGR/graph.json","events_json":"https://pith.science/api/pith-number/HLGOUZYU4TBFFZJIPTSXRWXBGR/events.json","paper":"https://pith.science/paper/HLGOUZYU"},"agent_actions":{"view_html":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR","download_json":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR.json","view_paper":"https://pith.science/paper/HLGOUZYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13826&json=true","fetch_graph":"https://pith.science/api/pith-number/HLGOUZYU4TBFFZJIPTSXRWXBGR/graph.json","fetch_events":"https://pith.science/api/pith-number/HLGOUZYU4TBFFZJIPTSXRWXBGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR/action/storage_attestation","attest_author":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR/action/author_attestation","sign_citation":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR/action/citation_signature","submit_replication":"https://pith.science/pith/HLGOUZYU4TBFFZJIPTSXRWXBGR/action/replication_record"}},"created_at":"2026-07-05T10:17:01.024770+00:00","updated_at":"2026-07-05T10:17:01.024770+00:00"}