{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:45XF3CSDW6XIBLIKSQZF4HOS6E","short_pith_number":"pith:45XF3CSD","schema_version":"1.0","canonical_sha256":"e76e5d8a43b7ae80ad0a94325e1dd2f11462a26c4862158ba804619f28a15f0d","source":{"kind":"arxiv","id":"2310.14021","version":1},"attestation_state":"computed","paper":{"title":"Survey of Vector Database Management Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Guoliang Li, James Jie Pan, Jianguo Wang","submitted_at":"2023-10-21T14:09:48Z","abstract_excerpt":"There are now over 20 commercial vector database management systems (VDBMSs), all produced within the past five years. But embedding-based retrieval has been studied for over ten years, and similarity search a staggering half century and more. Driving this shift from algorithms to systems are new data intensive applications, notably large language models, that demand vast stores of unstructured data coupled with reliable, secure, fast, and scalable query processing capability. A variety of new data management techniques now exist for addressing these needs, however there is no comprehensive su"},"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":"2310.14021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-10-21T14:09:48Z","cross_cats_sorted":[],"title_canon_sha256":"279eea15302899b5deaab5abbfaa0b3345515af3f1b35d211aa176eeede3d401","abstract_canon_sha256":"4ced320911a31dc5136d17e39794a84f0a9ef6801a4d37d897513f6abbbd9ad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:38.540404Z","signature_b64":"fOG2ypXHXm6lUn47RYMFUmvMoN49w8UBt7x859KIGxwMwsdcgupKHE5c5I0NFshKPva+eUnTqMIWaSYcEgo4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e76e5d8a43b7ae80ad0a94325e1dd2f11462a26c4862158ba804619f28a15f0d","last_reissued_at":"2026-07-05T07:03:38.539994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:38.539994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey of Vector Database Management Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Guoliang Li, James Jie Pan, Jianguo Wang","submitted_at":"2023-10-21T14:09:48Z","abstract_excerpt":"There are now over 20 commercial vector database management systems (VDBMSs), all produced within the past five years. But embedding-based retrieval has been studied for over ten years, and similarity search a staggering half century and more. Driving this shift from algorithms to systems are new data intensive applications, notably large language models, that demand vast stores of unstructured data coupled with reliable, secure, fast, and scalable query processing capability. A variety of new data management techniques now exist for addressing these needs, however there is no comprehensive su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14021","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/2310.14021/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":"2310.14021","created_at":"2026-07-05T07:03:38.540049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14021v1","created_at":"2026-07-05T07:03:38.540049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14021","created_at":"2026-07-05T07:03:38.540049+00:00"},{"alias_kind":"pith_short_12","alias_value":"45XF3CSDW6XI","created_at":"2026-07-05T07:03:38.540049+00:00"},{"alias_kind":"pith_short_16","alias_value":"45XF3CSDW6XIBLIK","created_at":"2026-07-05T07:03:38.540049+00:00"},{"alias_kind":"pith_short_8","alias_value":"45XF3CSD","created_at":"2026-07-05T07:03:38.540049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11789","citing_title":"Efficient Graph Indexing for Interval-Aware Vector Search","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07923","citing_title":"Larch: Learned Query Optimization for Semantic Predicates","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00768","citing_title":"RACORN-1: Adaptive Recall-Preserving Speedup for Low-Selectivity Filtered Vector Search","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01260","citing_title":"Write-Read Decoupling in Modern Large-Scale Search Engines: Architectures, Techniques, and Emerging Approaches","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E","json":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E.json","graph_json":"https://pith.science/api/pith-number/45XF3CSDW6XIBLIKSQZF4HOS6E/graph.json","events_json":"https://pith.science/api/pith-number/45XF3CSDW6XIBLIKSQZF4HOS6E/events.json","paper":"https://pith.science/paper/45XF3CSD"},"agent_actions":{"view_html":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E","download_json":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E.json","view_paper":"https://pith.science/paper/45XF3CSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14021&json=true","fetch_graph":"https://pith.science/api/pith-number/45XF3CSDW6XIBLIKSQZF4HOS6E/graph.json","fetch_events":"https://pith.science/api/pith-number/45XF3CSDW6XIBLIKSQZF4HOS6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E/action/storage_attestation","attest_author":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E/action/author_attestation","sign_citation":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E/action/citation_signature","submit_replication":"https://pith.science/pith/45XF3CSDW6XIBLIKSQZF4HOS6E/action/replication_record"}},"created_at":"2026-07-05T07:03:38.540049+00:00","updated_at":"2026-07-05T07:03:38.540049+00:00"}