{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y3HEGTFKUYY4UCCKRS4W7OT7BA","short_pith_number":"pith:Y3HEGTFK","schema_version":"1.0","canonical_sha256":"c6ce434caaa631ca084a8cb96fba7f082e6c54ba41d0784f2b947aca709cef93","source":{"kind":"arxiv","id":"2505.17152","version":2},"attestation_state":"computed","paper":{"title":"LSM-VEC: A Large-Scale Disk-Based System for Dynamic Vector Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dingheng Mo, Shurui Zhong, Siqiang Luo","submitted_at":"2025-05-22T11:11:02Z","abstract_excerpt":"Vector search underpins modern AI applications by supporting approximate nearest neighbor (ANN) queries over high-dimensional embeddings in tasks like retrieval-augmented generation (RAG), recommendation systems, and multimodal search. Traditional ANN search indices (e.g., HNSW) are limited by memory constraints at large data scale. Disk-based indices such as DiskANN reduce memory overhead but rely on offline graph construction, resulting in costly and inefficient vector updates. The state-of-the-art clustering-based approach SPFresh offers better scalability but suffers from reduced recall du"},"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":"2505.17152","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-05-22T11:11:02Z","cross_cats_sorted":[],"title_canon_sha256":"7e69660b9f742d520478765f2fbb96f4e2cc6410ebf638dd554eace45316440d","abstract_canon_sha256":"12d1cff26d15883ed83a8bd5ce6a43eed526c31c968f0d3ee6d9139c09e7fec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:50.518353Z","signature_b64":"RtocfAPzwpZ7O85e8Tt8URRTXWjzZK+XV8jJA+hKCNeu4BiAUG2T9m6OGHgLdNh/2KorqQLTauEXsh+Msl5dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ce434caaa631ca084a8cb96fba7f082e6c54ba41d0784f2b947aca709cef93","last_reissued_at":"2026-05-20T00:02:50.517505Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:50.517505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSM-VEC: A Large-Scale Disk-Based System for Dynamic Vector Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dingheng Mo, Shurui Zhong, Siqiang Luo","submitted_at":"2025-05-22T11:11:02Z","abstract_excerpt":"Vector search underpins modern AI applications by supporting approximate nearest neighbor (ANN) queries over high-dimensional embeddings in tasks like retrieval-augmented generation (RAG), recommendation systems, and multimodal search. Traditional ANN search indices (e.g., HNSW) are limited by memory constraints at large data scale. Disk-based indices such as DiskANN reduce memory overhead but rely on offline graph construction, resulting in costly and inefficient vector updates. The state-of-the-art clustering-based approach SPFresh offers better scalability but suffers from reduced recall du"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17152","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/2505.17152/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":"2505.17152","created_at":"2026-05-20T00:02:50.517631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17152v2","created_at":"2026-05-20T00:02:50.517631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17152","created_at":"2026-05-20T00:02:50.517631+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3HEGTFKUYY4","created_at":"2026-05-20T00:02:50.517631+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3HEGTFKUYY4UCCK","created_at":"2026-05-20T00:02:50.517631+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3HEGTFK","created_at":"2026-05-20T00:02:50.517631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.02522","citing_title":"Opal: Private Memory for Personal AI","ref_index":281,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA","json":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA.json","graph_json":"https://pith.science/api/pith-number/Y3HEGTFKUYY4UCCKRS4W7OT7BA/graph.json","events_json":"https://pith.science/api/pith-number/Y3HEGTFKUYY4UCCKRS4W7OT7BA/events.json","paper":"https://pith.science/paper/Y3HEGTFK"},"agent_actions":{"view_html":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA","download_json":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA.json","view_paper":"https://pith.science/paper/Y3HEGTFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17152&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3HEGTFKUYY4UCCKRS4W7OT7BA/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3HEGTFKUYY4UCCKRS4W7OT7BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA/action/storage_attestation","attest_author":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA/action/author_attestation","sign_citation":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA/action/citation_signature","submit_replication":"https://pith.science/pith/Y3HEGTFKUYY4UCCKRS4W7OT7BA/action/replication_record"}},"created_at":"2026-05-20T00:02:50.517631+00:00","updated_at":"2026-05-20T00:02:50.517631+00:00"}