{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UJY23HJCTPDKMCA34W4EMXYRXU","short_pith_number":"pith:UJY23HJC","schema_version":"1.0","canonical_sha256":"a271ad9d229bc6a6081be5b8465f11bd11033635dbf0fac11eb0e940809be0c7","source":{"kind":"arxiv","id":"1804.06829","version":2},"attestation_state":"computed","paper":{"title":"HD-Index: Pushing the Scalability-Accuracy Boundary for Approximate kNN Search in High-Dimensional Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Akhil Arora, Arnab Bhattacharya, Piyush Kumar, Sakshi Sinha","submitted_at":"2018-04-18T17:28:48Z","abstract_excerpt":"Nearest neighbor searching of large databases in high-dimensional spaces is inherently difficult due to the curse of dimensionality. A flavor of approximation is, therefore, necessary to practically solve the problem of nearest neighbor search. In this paper, we propose a novel yet simple indexing scheme, HD-Index, to solve the problem of approximate k-nearest neighbor queries in massive high-dimensional databases. HD-Index consists of a set of novel hierarchical structures called RDB-trees built on Hilbert keys of database objects. The leaves of the RDB-trees store distances of database objec"},"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":"1804.06829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-04-18T17:28:48Z","cross_cats_sorted":[],"title_canon_sha256":"bd07459ca5e3bce62e127cfef1f0ad832101edb3c038c78436c556507f1d99a7","abstract_canon_sha256":"e7fa48edfcbe5cce5489d3d6055d649b2ea5f90e53b0e095cf95f672c6f9990c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:52.938905Z","signature_b64":"LrZxIGCl3asgxwv+DD9Iif00iFj84ozxwhKSUB+J0EEJRCeW7q5RD8pXRHZypUhK50wRTG/Iz2u1UYJoQr5CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a271ad9d229bc6a6081be5b8465f11bd11033635dbf0fac11eb0e940809be0c7","last_reissued_at":"2026-05-18T00:17:52.938294Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:52.938294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HD-Index: Pushing the Scalability-Accuracy Boundary for Approximate kNN Search in High-Dimensional Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Akhil Arora, Arnab Bhattacharya, Piyush Kumar, Sakshi Sinha","submitted_at":"2018-04-18T17:28:48Z","abstract_excerpt":"Nearest neighbor searching of large databases in high-dimensional spaces is inherently difficult due to the curse of dimensionality. A flavor of approximation is, therefore, necessary to practically solve the problem of nearest neighbor search. In this paper, we propose a novel yet simple indexing scheme, HD-Index, to solve the problem of approximate k-nearest neighbor queries in massive high-dimensional databases. HD-Index consists of a set of novel hierarchical structures called RDB-trees built on Hilbert keys of database objects. The leaves of the RDB-trees store distances of database objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06829","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":""},"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":"1804.06829","created_at":"2026-05-18T00:17:52.938386+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06829v2","created_at":"2026-05-18T00:17:52.938386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06829","created_at":"2026-05-18T00:17:52.938386+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJY23HJCTPDK","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJY23HJCTPDKMCA3","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJY23HJC","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17152","citing_title":"LSM-VEC: A Large-Scale Disk-Based System for Dynamic Vector Search","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU","json":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU.json","graph_json":"https://pith.science/api/pith-number/UJY23HJCTPDKMCA34W4EMXYRXU/graph.json","events_json":"https://pith.science/api/pith-number/UJY23HJCTPDKMCA34W4EMXYRXU/events.json","paper":"https://pith.science/paper/UJY23HJC"},"agent_actions":{"view_html":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU","download_json":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU.json","view_paper":"https://pith.science/paper/UJY23HJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06829&json=true","fetch_graph":"https://pith.science/api/pith-number/UJY23HJCTPDKMCA34W4EMXYRXU/graph.json","fetch_events":"https://pith.science/api/pith-number/UJY23HJCTPDKMCA34W4EMXYRXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU/action/storage_attestation","attest_author":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU/action/author_attestation","sign_citation":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU/action/citation_signature","submit_replication":"https://pith.science/pith/UJY23HJCTPDKMCA34W4EMXYRXU/action/replication_record"}},"created_at":"2026-05-18T00:17:52.938386+00:00","updated_at":"2026-05-18T00:17:52.938386+00:00"}