{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:JZIP526ERWNXXPY5MVQFF56FOH","short_pith_number":"pith:JZIP526E","schema_version":"1.0","canonical_sha256":"4e50feebc48d9b7bbf1d656052f7c571e60c8a2a169b45e8fc41f630fd29bd66","source":{"kind":"arxiv","id":"1206.6411","version":1},"attestation_state":"computed","paper":{"title":"On the Difficulty of Nearest Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junfeng He (Columbia University), Sanjiv Kumar (Google Research), Shih-Fu Chang (Columbia University)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"Fast approximate nearest neighbor (NN) search in large databases is becoming popular. Several powerful learning-based formulations have been proposed recently. However, not much attention has been paid to a more fundamental question: how difficult is (approximate) nearest neighbor search in a given data set? And which data properties affect the difficulty of nearest neighbor search and how? This paper introduces the first concrete measure called Relative Contrast that can be used to evaluate the influence of several crucial data characteristics such as dimensionality, sparsity, and database si"},"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":"1206.6411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","cross_cats_sorted":["cs.DB","cs.IR","stat.ML"],"title_canon_sha256":"07e123128eb2c831c8e68b746bd5fb11d286a378fb942dae9105e042668bdecc","abstract_canon_sha256":"c72ec167660aeb64d325e4756e029f6170aecb8c040a4b948869e397bcae17de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:14.364658Z","signature_b64":"Jp6/0rGTLddKS/rGKqp9/LjJquaMiigBxWqtPdR1OX3E7LMbgqQAtDX9J/0KlatL/Dr7wRYrJB2DqGaWAqqtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e50feebc48d9b7bbf1d656052f7c571e60c8a2a169b45e8fc41f630fd29bd66","last_reissued_at":"2026-05-18T03:52:14.364150Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:14.364150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Difficulty of Nearest Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junfeng He (Columbia University), Sanjiv Kumar (Google Research), Shih-Fu Chang (Columbia University)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"Fast approximate nearest neighbor (NN) search in large databases is becoming popular. Several powerful learning-based formulations have been proposed recently. However, not much attention has been paid to a more fundamental question: how difficult is (approximate) nearest neighbor search in a given data set? And which data properties affect the difficulty of nearest neighbor search and how? This paper introduces the first concrete measure called Relative Contrast that can be used to evaluate the influence of several crucial data characteristics such as dimensionality, sparsity, and database si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6411","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":""},"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":"1206.6411","created_at":"2026-05-18T03:52:14.364224+00:00"},{"alias_kind":"arxiv_version","alias_value":"1206.6411v1","created_at":"2026-05-18T03:52:14.364224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6411","created_at":"2026-05-18T03:52:14.364224+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZIP526ERWNX","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZIP526ERWNXXPY5","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZIP526E","created_at":"2026-05-18T12:27:11.947152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05750","citing_title":"Toward Efficient and Scalable Design of In-Memory Graph-Based Vector Search","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH","json":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH.json","graph_json":"https://pith.science/api/pith-number/JZIP526ERWNXXPY5MVQFF56FOH/graph.json","events_json":"https://pith.science/api/pith-number/JZIP526ERWNXXPY5MVQFF56FOH/events.json","paper":"https://pith.science/paper/JZIP526E"},"agent_actions":{"view_html":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH","download_json":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH.json","view_paper":"https://pith.science/paper/JZIP526E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1206.6411&json=true","fetch_graph":"https://pith.science/api/pith-number/JZIP526ERWNXXPY5MVQFF56FOH/graph.json","fetch_events":"https://pith.science/api/pith-number/JZIP526ERWNXXPY5MVQFF56FOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH/action/storage_attestation","attest_author":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH/action/author_attestation","sign_citation":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH/action/citation_signature","submit_replication":"https://pith.science/pith/JZIP526ERWNXXPY5MVQFF56FOH/action/replication_record"}},"created_at":"2026-05-18T03:52:14.364224+00:00","updated_at":"2026-05-18T03:52:14.364224+00:00"}