{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J3C4XCRYGKIQ2G2IZDFNJ6CP47","short_pith_number":"pith:J3C4XCRY","schema_version":"1.0","canonical_sha256":"4ec5cb8a3832910d1b48c8cad4f84fe7e5177baf96f25bedea0c6deca7859f7b","source":{"kind":"arxiv","id":"2111.08566","version":1},"attestation_state":"computed","paper":{"title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.DB","authors_text":"Bing Zhao, Chuanjie Liu, Haidong Wang, Jingdong Wang, Mao Yang, Mingqin Li, Qi Chen, Zengzhong Li","submitted_at":"2021-11-05T06:28:15Z","abstract_excerpt":"The in-memory algorithms for approximate nearest neighbor search (ANNS) have achieved great success for fast high-recall search, but are extremely expensive when handling very large scale database. Thus, there is an increasing request for the hybrid ANNS solutions with small memory and inexpensive solid-state drive (SSD). In this paper, we present a simple but efficient memory-disk hybrid indexing and search system, named SPANN, that follows the inverted index methodology. It stores the centroid points of the posting lists in the memory and the large posting lists in the disk. We guarantee bot"},"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":"2111.08566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-11-05T06:28:15Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"e905346c46514b0e6518f1f60a4de944e4f0d76bdae4d0dc7e773075a0585adc","abstract_canon_sha256":"3a0fcf675ba8119220dd373d73b2ebd3037b545f777a802cb00dd231fc5344cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:35.293904Z","signature_b64":"Dxq2COVIpC0Om9RFV5AxPbQ7W/TeRFArVSQcP0FiK0paUXVj5XF+nNpaHlwjSRNz1sIMNx+DABaWIkpzSROYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ec5cb8a3832910d1b48c8cad4f84fe7e5177baf96f25bedea0c6deca7859f7b","last_reissued_at":"2026-07-05T03:32:35.293404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:35.293404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.DB","authors_text":"Bing Zhao, Chuanjie Liu, Haidong Wang, Jingdong Wang, Mao Yang, Mingqin Li, Qi Chen, Zengzhong Li","submitted_at":"2021-11-05T06:28:15Z","abstract_excerpt":"The in-memory algorithms for approximate nearest neighbor search (ANNS) have achieved great success for fast high-recall search, but are extremely expensive when handling very large scale database. Thus, there is an increasing request for the hybrid ANNS solutions with small memory and inexpensive solid-state drive (SSD). In this paper, we present a simple but efficient memory-disk hybrid indexing and search system, named SPANN, that follows the inverted index methodology. It stores the centroid points of the posting lists in the memory and the large posting lists in the disk. We guarantee bot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08566","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/2111.08566/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":"2111.08566","created_at":"2026-07-05T03:32:35.293470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08566v1","created_at":"2026-07-05T03:32:35.293470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08566","created_at":"2026-07-05T03:32:35.293470+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3C4XCRYGKIQ","created_at":"2026-07-05T03:32:35.293470+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3C4XCRYGKIQ2G2I","created_at":"2026-07-05T03:32:35.293470+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3C4XCRY","created_at":"2026-07-05T03:32:35.293470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09441","citing_title":"SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance","ref_index":4,"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":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47","json":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47.json","graph_json":"https://pith.science/api/pith-number/J3C4XCRYGKIQ2G2IZDFNJ6CP47/graph.json","events_json":"https://pith.science/api/pith-number/J3C4XCRYGKIQ2G2IZDFNJ6CP47/events.json","paper":"https://pith.science/paper/J3C4XCRY"},"agent_actions":{"view_html":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47","download_json":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47.json","view_paper":"https://pith.science/paper/J3C4XCRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08566&json=true","fetch_graph":"https://pith.science/api/pith-number/J3C4XCRYGKIQ2G2IZDFNJ6CP47/graph.json","fetch_events":"https://pith.science/api/pith-number/J3C4XCRYGKIQ2G2IZDFNJ6CP47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47/action/storage_attestation","attest_author":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47/action/author_attestation","sign_citation":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47/action/citation_signature","submit_replication":"https://pith.science/pith/J3C4XCRYGKIQ2G2IZDFNJ6CP47/action/replication_record"}},"created_at":"2026-07-05T03:32:35.293470+00:00","updated_at":"2026-07-05T03:32:35.293470+00:00"}