{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RIVF4YFHCBYGFMNGUREEPIBHAE","short_pith_number":"pith:RIVF4YFH","schema_version":"1.0","canonical_sha256":"8a2a5e60a7107062b1a6a44847a0270118a8ddeca88a073975db9c0f12072657","source":{"kind":"arxiv","id":"1603.09320","version":4},"attestation_state":"computed","paper":{"title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR","cs.SI"],"primary_cat":"cs.DS","authors_text":"D. A. Yashunin, Yu. A. Malkov","submitted_at":"2016-03-30T19:29:44Z","abstract_excerpt":"We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The proposed solution is fully graph-based, without any need for additional search structures, which are typically used at the coarse search stage of the most proximity graph techniques. Hierarchical NSW incrementally builds a multi-layer structure consisting from hierarchical set of proximity graphs (layers) for nested subsets of the stored elements. The maximum layer in which an element is present is selected randomly with an expo"},"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":"1603.09320","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2016-03-30T19:29:44Z","cross_cats_sorted":["cs.CV","cs.IR","cs.SI"],"title_canon_sha256":"f695261b1715eb6e5dcdc31c9840417c6f2901907814b2c2b3dee7b35ab7180c","abstract_canon_sha256":"2430158b32f9db5803c28bf9f6340c837390503bfa044a9cc89d9bb5f77c7f06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:05.404182Z","signature_b64":"MSzVFqd7+Sduz0yO2o2cm58D5mDYe7w/XEZAWNubFyZVvsudbcm/eFe9kFd6l0toWVGR4JyCmj5DiEvSVGRKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a2a5e60a7107062b1a6a44847a0270118a8ddeca88a073975db9c0f12072657","last_reissued_at":"2026-05-18T00:08:05.403699Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:05.403699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR","cs.SI"],"primary_cat":"cs.DS","authors_text":"D. A. Yashunin, Yu. A. Malkov","submitted_at":"2016-03-30T19:29:44Z","abstract_excerpt":"We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The proposed solution is fully graph-based, without any need for additional search structures, which are typically used at the coarse search stage of the most proximity graph techniques. Hierarchical NSW incrementally builds a multi-layer structure consisting from hierarchical set of proximity graphs (layers) for nested subsets of the stored elements. The maximum layer in which an element is present is selected randomly with an expo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09320","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1603.09320","created_at":"2026-05-18T00:08:05.403771+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.09320v4","created_at":"2026-05-18T00:08:05.403771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09320","created_at":"2026-05-18T00:08:05.403771+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIVF4YFHCBYG","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIVF4YFHCBYGFMNG","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIVF4YFH","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.12211","citing_title":"PUFFINN: Parameterless and Universally Fast FInding of Nearest Neighbors","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18850","citing_title":"KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00779","citing_title":"Using predefined vector systems to speed up neural network multimillion class classification","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04897","citing_title":"Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11274","citing_title":"Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2005.11401","citing_title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE","json":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE.json","graph_json":"https://pith.science/api/pith-number/RIVF4YFHCBYGFMNGUREEPIBHAE/graph.json","events_json":"https://pith.science/api/pith-number/RIVF4YFHCBYGFMNGUREEPIBHAE/events.json","paper":"https://pith.science/paper/RIVF4YFH"},"agent_actions":{"view_html":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE","download_json":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE.json","view_paper":"https://pith.science/paper/RIVF4YFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.09320&json=true","fetch_graph":"https://pith.science/api/pith-number/RIVF4YFHCBYGFMNGUREEPIBHAE/graph.json","fetch_events":"https://pith.science/api/pith-number/RIVF4YFHCBYGFMNGUREEPIBHAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE/action/storage_attestation","attest_author":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE/action/author_attestation","sign_citation":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE/action/citation_signature","submit_replication":"https://pith.science/pith/RIVF4YFHCBYGFMNGUREEPIBHAE/action/replication_record"}},"created_at":"2026-05-18T00:08:05.403771+00:00","updated_at":"2026-05-18T00:08:05.403771+00:00"}