{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MRUM4JJGQ7QKQIITYSHDAIZ6N2","short_pith_number":"pith:MRUM4JJG","schema_version":"1.0","canonical_sha256":"6468ce252687e0a82113c48e30233e6e85df60cd85fc3354f6edc30ccc90276f","source":{"kind":"arxiv","id":"1610.10001","version":1},"attestation_state":"computed","paper":{"title":"Off the Beaten Path: Let's Replace Term-Based Retrieval with k-NN Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"David Novak, Eric Nyberg, Leonid Boytsov, Yury Malkov","submitted_at":"2016-10-31T16:27:08Z","abstract_excerpt":"Retrieval pipelines commonly rely on a term-based search to obtain candidate records, which are subsequently re-ranked. Some candidates are missed by this approach, e.g., due to a vocabulary mismatch. We address this issue by replacing the term-based search with a generic k-NN retrieval algorithm, where a similarity function can take into account subtle term associations. While an exact brute-force k-NN search using this similarity function is slow, we demonstrate that an approximate algorithm can be nearly two orders of magnitude faster at the expense of only a small loss in accuracy. A retri"},"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":"1610.10001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-10-31T16:27:08Z","cross_cats_sorted":[],"title_canon_sha256":"e0cc262719ffd48de03f272843c53981fb35d4dfe7d13ff62679f950bd0788c7","abstract_canon_sha256":"2259f4785292d937667c83f945dbb2bf08c99924aa6dd3de9355eb3cd4149130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:46.758002Z","signature_b64":"CDXCoE2UCbwY5/FT1hk9FP8iNfK8zU01ilFx60IQNQ/vb3091YsQbXWTwiYsovWkvtkQugmhp/8aKBr53RbDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6468ce252687e0a82113c48e30233e6e85df60cd85fc3354f6edc30ccc90276f","last_reissued_at":"2026-05-18T01:00:46.757531Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:46.757531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off the Beaten Path: Let's Replace Term-Based Retrieval with k-NN Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"David Novak, Eric Nyberg, Leonid Boytsov, Yury Malkov","submitted_at":"2016-10-31T16:27:08Z","abstract_excerpt":"Retrieval pipelines commonly rely on a term-based search to obtain candidate records, which are subsequently re-ranked. Some candidates are missed by this approach, e.g., due to a vocabulary mismatch. We address this issue by replacing the term-based search with a generic k-NN retrieval algorithm, where a similarity function can take into account subtle term associations. While an exact brute-force k-NN search using this similarity function is slow, we demonstrate that an approximate algorithm can be nearly two orders of magnitude faster at the expense of only a small loss in accuracy. A retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.10001","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":"1610.10001","created_at":"2026-05-18T01:00:46.757622+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.10001v1","created_at":"2026-05-18T01:00:46.757622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.10001","created_at":"2026-05-18T01:00:46.757622+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRUM4JJGQ7QK","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRUM4JJGQ7QKQIIT","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRUM4JJG","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2","json":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2.json","graph_json":"https://pith.science/api/pith-number/MRUM4JJGQ7QKQIITYSHDAIZ6N2/graph.json","events_json":"https://pith.science/api/pith-number/MRUM4JJGQ7QKQIITYSHDAIZ6N2/events.json","paper":"https://pith.science/paper/MRUM4JJG"},"agent_actions":{"view_html":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2","download_json":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2.json","view_paper":"https://pith.science/paper/MRUM4JJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.10001&json=true","fetch_graph":"https://pith.science/api/pith-number/MRUM4JJGQ7QKQIITYSHDAIZ6N2/graph.json","fetch_events":"https://pith.science/api/pith-number/MRUM4JJGQ7QKQIITYSHDAIZ6N2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2/action/storage_attestation","attest_author":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2/action/author_attestation","sign_citation":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2/action/citation_signature","submit_replication":"https://pith.science/pith/MRUM4JJGQ7QKQIITYSHDAIZ6N2/action/replication_record"}},"created_at":"2026-05-18T01:00:46.757622+00:00","updated_at":"2026-05-18T01:00:46.757622+00:00"}