{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4LBX7WL3VQM45HWZEQZZZQJJYF","short_pith_number":"pith:4LBX7WL3","schema_version":"1.0","canonical_sha256":"e2c37fd97bac19ce9ed924339cc129c15118a646deb104218513c1cebb371305","source":{"kind":"arxiv","id":"2305.04359","version":2},"attestation_state":"computed","paper":{"title":"ParlayANN: Scalable and Deterministic Parallel Graph-Based Approximate Nearest Neighbor Search Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Guy E. Blelloch, Harsha Vardhan Simhadri, Laxman Dhulipala, Magdalen Dobson Manohar, Yan Gu, Yihan Sun, Zheqi Shen","submitted_at":"2023-05-07T19:28:23Z","abstract_excerpt":"Approximate nearest-neighbor search (ANNS) algorithms are a key part of the modern deep learning stack due to enabling efficient similarity search over high-dimensional vector space representations (i.e., embeddings) of data. Among various ANNS algorithms, graph-based algorithms are known to achieve the best throughput-recall tradeoffs. Despite the large scale of modern ANNS datasets, existing parallel graph based implementations suffer from significant challenges to scale to large datasets due to heavy use of locks and other sequential bottlenecks, which 1) prevents them from efficiently scal"},"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":"2305.04359","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-07T19:28:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ba44d14ccd4949e5c8142c0dd64fa1228af1a92401427e99db069bf006643fa9","abstract_canon_sha256":"c8786745d9b3ac5dd202e0b62d132bf2db0b7b72ce1754074ceed27da4fabb7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:00.015995Z","signature_b64":"wRSP8zRtKgzHBGF0xE2u0eLxryFPudxL8ZV3Kkh2cGbWZCboHRsZwpkGf3CbOGYNWhuonBQH4LEs5FLwPDibBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2c37fd97bac19ce9ed924339cc129c15118a646deb104218513c1cebb371305","last_reissued_at":"2026-07-05T07:43:00.015484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:00.015484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParlayANN: Scalable and Deterministic Parallel Graph-Based Approximate Nearest Neighbor Search Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Guy E. Blelloch, Harsha Vardhan Simhadri, Laxman Dhulipala, Magdalen Dobson Manohar, Yan Gu, Yihan Sun, Zheqi Shen","submitted_at":"2023-05-07T19:28:23Z","abstract_excerpt":"Approximate nearest-neighbor search (ANNS) algorithms are a key part of the modern deep learning stack due to enabling efficient similarity search over high-dimensional vector space representations (i.e., embeddings) of data. Among various ANNS algorithms, graph-based algorithms are known to achieve the best throughput-recall tradeoffs. Despite the large scale of modern ANNS datasets, existing parallel graph based implementations suffer from significant challenges to scale to large datasets due to heavy use of locks and other sequential bottlenecks, which 1) prevents them from efficiently scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04359","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/2305.04359/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":"2305.04359","created_at":"2026-07-05T07:43:00.015541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04359v2","created_at":"2026-07-05T07:43:00.015541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04359","created_at":"2026-07-05T07:43:00.015541+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LBX7WL3VQM4","created_at":"2026-07-05T07:43:00.015541+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LBX7WL3VQM45HWZ","created_at":"2026-07-05T07:43:00.015541+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LBX7WL3","created_at":"2026-07-05T07:43:00.015541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11789","citing_title":"Efficient Graph Indexing for Interval-Aware Vector Search","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12913","citing_title":"RNSG: A Range-Aware Graph Index for Efficient Range-Filtered Approximate Nearest Neighbor Search","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01960","citing_title":"BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF","json":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF.json","graph_json":"https://pith.science/api/pith-number/4LBX7WL3VQM45HWZEQZZZQJJYF/graph.json","events_json":"https://pith.science/api/pith-number/4LBX7WL3VQM45HWZEQZZZQJJYF/events.json","paper":"https://pith.science/paper/4LBX7WL3"},"agent_actions":{"view_html":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF","download_json":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF.json","view_paper":"https://pith.science/paper/4LBX7WL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04359&json=true","fetch_graph":"https://pith.science/api/pith-number/4LBX7WL3VQM45HWZEQZZZQJJYF/graph.json","fetch_events":"https://pith.science/api/pith-number/4LBX7WL3VQM45HWZEQZZZQJJYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF/action/storage_attestation","attest_author":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF/action/author_attestation","sign_citation":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF/action/citation_signature","submit_replication":"https://pith.science/pith/4LBX7WL3VQM45HWZEQZZZQJJYF/action/replication_record"}},"created_at":"2026-07-05T07:43:00.015541+00:00","updated_at":"2026-07-05T07:43:00.015541+00:00"}