{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HWBPNKDYSIJFFXQDRKSWMQA5LY","short_pith_number":"pith:HWBPNKDY","schema_version":"1.0","canonical_sha256":"3d82f6a878921252de038aa566401d5e34d07fd245ee8b86c6ce2f3da5b2f9f4","source":{"kind":"arxiv","id":"2205.03763","version":1},"attestation_state":"computed","paper":{"title":"Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DB","cs.DS","cs.PF"],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Dmitry Baranchuk, George Williams, Gopal Srinivasa, Harsha Vardhan Simhadri, Jingdong Wang, Lucas Hosseini, Martin Aum\\\"uller, Matthijs Douze, Qi Chen, Ravishankar Krishnaswamy, Suhas Jayaram Subramanya","submitted_at":"2022-05-08T02:41:54Z","abstract_excerpt":"Despite the broad range of algorithms for Approximate Nearest Neighbor Search, most empirical evaluations of algorithms have focused on smaller datasets, typically of 1 million points~\\citep{Benchmark}. However, deploying recent advances in embedding based techniques for search, recommendation and ranking at scale require ANNS indices at billion, trillion or larger scale. Barring a few recent papers, there is limited consensus on which algorithms are effective at this scale vis-\\`a-vis their hardware cost.\n  This competition compares ANNS algorithms at billion-scale by hardware cost, accuracy "},"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":"2205.03763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-08T02:41:54Z","cross_cats_sorted":["cs.DB","cs.DS","cs.PF"],"title_canon_sha256":"5c9aee9e6ba29397e56d5bc3d1a0147e88a7dfb908e15f6676de1ade2ab240b3","abstract_canon_sha256":"978d9440127f83f28bfd46172785e73b9f2651d7ff3e37c99b77d226eda05ea5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:18.321968Z","signature_b64":"VRhYkZqwGkl55eiMloIV92bHYCkyvLNqzCB8fHpY7lRHvOezXnxt/Wi69o+qkNU1tH8G4/yKCPUvTp2kcUXpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d82f6a878921252de038aa566401d5e34d07fd245ee8b86c6ce2f3da5b2f9f4","last_reissued_at":"2026-07-05T04:21:18.321224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:18.321224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DB","cs.DS","cs.PF"],"primary_cat":"cs.LG","authors_text":"Artem Babenko, Dmitry Baranchuk, George Williams, Gopal Srinivasa, Harsha Vardhan Simhadri, Jingdong Wang, Lucas Hosseini, Martin Aum\\\"uller, Matthijs Douze, Qi Chen, Ravishankar Krishnaswamy, Suhas Jayaram Subramanya","submitted_at":"2022-05-08T02:41:54Z","abstract_excerpt":"Despite the broad range of algorithms for Approximate Nearest Neighbor Search, most empirical evaluations of algorithms have focused on smaller datasets, typically of 1 million points~\\citep{Benchmark}. However, deploying recent advances in embedding based techniques for search, recommendation and ranking at scale require ANNS indices at billion, trillion or larger scale. Barring a few recent papers, there is limited consensus on which algorithms are effective at this scale vis-\\`a-vis their hardware cost.\n  This competition compares ANNS algorithms at billion-scale by hardware cost, accuracy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03763","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/2205.03763/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":"2205.03763","created_at":"2026-07-05T04:21:18.321301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03763v1","created_at":"2026-07-05T04:21:18.321301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03763","created_at":"2026-07-05T04:21:18.321301+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWBPNKDYSIJF","created_at":"2026-07-05T04:21:18.321301+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWBPNKDYSIJFFXQD","created_at":"2026-07-05T04:21:18.321301+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWBPNKDY","created_at":"2026-07-05T04:21:18.321301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00768","citing_title":"RACORN-1: Adaptive Recall-Preserving Speedup for Low-Selectivity Filtered Vector Search","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY","json":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY.json","graph_json":"https://pith.science/api/pith-number/HWBPNKDYSIJFFXQDRKSWMQA5LY/graph.json","events_json":"https://pith.science/api/pith-number/HWBPNKDYSIJFFXQDRKSWMQA5LY/events.json","paper":"https://pith.science/paper/HWBPNKDY"},"agent_actions":{"view_html":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY","download_json":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY.json","view_paper":"https://pith.science/paper/HWBPNKDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03763&json=true","fetch_graph":"https://pith.science/api/pith-number/HWBPNKDYSIJFFXQDRKSWMQA5LY/graph.json","fetch_events":"https://pith.science/api/pith-number/HWBPNKDYSIJFFXQDRKSWMQA5LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY/action/storage_attestation","attest_author":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY/action/author_attestation","sign_citation":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY/action/citation_signature","submit_replication":"https://pith.science/pith/HWBPNKDYSIJFFXQDRKSWMQA5LY/action/replication_record"}},"created_at":"2026-07-05T04:21:18.321301+00:00","updated_at":"2026-07-05T04:21:18.321301+00:00"}