{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VTB7U3YPSB2USQRUPI343NLYRN","short_pith_number":"pith:VTB7U3YP","schema_version":"1.0","canonical_sha256":"acc3fa6f0f90754942347a37cdb5788b74605cbae903748aced2eb2a87700dfd","source":{"kind":"arxiv","id":"2507.19802","version":1},"attestation_state":"computed","paper":{"title":"CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DC","cs.DS","cs.IR"],"primary_cat":"cs.DB","authors_text":"Joshua Engels, Julian Shun, Yuanhao Wei, Ziyu Zhang","submitted_at":"2025-07-26T05:27:32Z","abstract_excerpt":"Approximate nearest neighbor search (ANNS) has become a quintessential algorithmic problem for various other foundational data tasks for AI workloads. Graph-based ANNS indexes have superb empirical trade-offs in indexing cost, query efficiency, and query approximation quality. Most existing graph-based indexes are designed for the static scenario, where there are no updates to the data after the index is constructed. However, full dynamism (insertions, deletions, and searches) is crucial to providing up-to-date responses in applications using vector databases. It is desirable that the index ef"},"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":"2507.19802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-26T05:27:32Z","cross_cats_sorted":["cs.DC","cs.DS","cs.IR"],"title_canon_sha256":"c0442628e34ebc5309724c8c572ca604903e0c38532bc42047c2691c0a0894c0","abstract_canon_sha256":"f277dc11a2c1384b090b254549229bf0f2002952572bc38c9899c7a2da0c9305"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:15.592604Z","signature_b64":"7dbxdACA3RmBtYp+KR256dfvzIeG8rjH0hYryozNDmTFaAJOiZcl6V0MA/VHtWjKmU0o4wkEsWbOl1/W4f+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc3fa6f0f90754942347a37cdb5788b74605cbae903748aced2eb2a87700dfd","last_reissued_at":"2026-07-05T11:45:15.592063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:15.592063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DC","cs.DS","cs.IR"],"primary_cat":"cs.DB","authors_text":"Joshua Engels, Julian Shun, Yuanhao Wei, Ziyu Zhang","submitted_at":"2025-07-26T05:27:32Z","abstract_excerpt":"Approximate nearest neighbor search (ANNS) has become a quintessential algorithmic problem for various other foundational data tasks for AI workloads. Graph-based ANNS indexes have superb empirical trade-offs in indexing cost, query efficiency, and query approximation quality. Most existing graph-based indexes are designed for the static scenario, where there are no updates to the data after the index is constructed. However, full dynamism (insertions, deletions, and searches) is crucial to providing up-to-date responses in applications using vector databases. It is desirable that the index ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19802","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/2507.19802/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":"2507.19802","created_at":"2026-07-05T11:45:15.592124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19802v1","created_at":"2026-07-05T11:45:15.592124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19802","created_at":"2026-07-05T11:45:15.592124+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTB7U3YPSB2U","created_at":"2026-07-05T11:45:15.592124+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTB7U3YPSB2USQRU","created_at":"2026-07-05T11:45:15.592124+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTB7U3YP","created_at":"2026-07-05T11:45:15.592124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.03151","citing_title":"ACRONYM: Accelerated Approximate Nearest Neighbor Search in Memory for Dynamic Vector Databases","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02992","citing_title":"Slipstream: Locality-Aware Graph Index Construction for Streaming Approximate Nearest Neighbor Search","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23887","citing_title":"CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces","ref_index":80,"is_internal_anchor":true},{"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":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN","json":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN.json","graph_json":"https://pith.science/api/pith-number/VTB7U3YPSB2USQRUPI343NLYRN/graph.json","events_json":"https://pith.science/api/pith-number/VTB7U3YPSB2USQRUPI343NLYRN/events.json","paper":"https://pith.science/paper/VTB7U3YP"},"agent_actions":{"view_html":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN","download_json":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN.json","view_paper":"https://pith.science/paper/VTB7U3YP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19802&json=true","fetch_graph":"https://pith.science/api/pith-number/VTB7U3YPSB2USQRUPI343NLYRN/graph.json","fetch_events":"https://pith.science/api/pith-number/VTB7U3YPSB2USQRUPI343NLYRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN/action/storage_attestation","attest_author":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN/action/author_attestation","sign_citation":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN/action/citation_signature","submit_replication":"https://pith.science/pith/VTB7U3YPSB2USQRUPI343NLYRN/action/replication_record"}},"created_at":"2026-07-05T11:45:15.592124+00:00","updated_at":"2026-07-05T11:45:15.592124+00:00"}