{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HWGQFLBN273CPKSDZF2DDEYGUB","short_pith_number":"pith:HWGQFLBN","schema_version":"1.0","canonical_sha256":"3d8d02ac2dd7f627aa43c974319306a05afc69ae19fec5df9608662f9bc63f8a","source":{"kind":"arxiv","id":"2604.01960","version":3},"attestation_state":"computed","paper":{"title":"BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A bucket-based collector organizes ANN candidates by distance to speed up large-k queries in quantization indexes by up to 3.8 times.","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Bin Cui, Gao Cong, Jinwei Zhu, Kai Zeng, Ziqi Yin","submitted_at":"2026-04-02T12:22:38Z","abstract_excerpt":"Although Approximate Nearest Neighbor (ANN) search has been extensively studied, large-k ANN queries that aim to retrieve a large number of nearest neighbors remain underexplored, despite their numerous real-world applications. Existing ANN methods face significant performance degradation for such queries. In this work, we first investigate the reasons for the performance degradation of quantization-based ANN indexes: (1) the inefficiency of existing top-k collectors, which incurs significant overhead in candidate maintenance, and (2) the reduced pruning effectiveness of quantization methods, "},"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":true},"canonical_record":{"source":{"id":"2604.01960","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-04-02T12:22:38Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"60bab5b969a9b1453a4475c9b077b702d588c19ffa20fc516e462ff9be81bf86","abstract_canon_sha256":"9833e17833692bf0d9b2f0e01c5d7c410e2610b587677ef7a07ac6b6f53216ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:12.435831Z","signature_b64":"R/w2kTcOgikoeka9jO+ZDJM5cFAWZYhykaL39PTyXRkjv6s1uQFwe4pihhOhUPnPmvIpnBWW0EcAAgt3LsfKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d8d02ac2dd7f627aa43c974319306a05afc69ae19fec5df9608662f9bc63f8a","last_reissued_at":"2026-06-03T01:05:12.435297Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:12.435297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A bucket-based collector organizes ANN candidates by distance to speed up large-k queries in quantization indexes by up to 3.8 times.","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Bin Cui, Gao Cong, Jinwei Zhu, Kai Zeng, Ziqi Yin","submitted_at":"2026-04-02T12:22:38Z","abstract_excerpt":"Although Approximate Nearest Neighbor (ANN) search has been extensively studied, large-k ANN queries that aim to retrieve a large number of nearest neighbors remain underexplored, despite their numerous real-world applications. Existing ANN methods face significant performance degradation for such queries. In this work, we first investigate the reasons for the performance degradation of quantization-based ANN indexes: (1) the inefficiency of existing top-k collectors, which incurs significant overhead in candidate maintenance, and (2) the reduced pruning effectiveness of quantization methods, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"BBC accelerates existing quantization-based ANN methods by up to 3.8x at recall@k = 0.95 for large-k ANN queries.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That organizing candidates into distance-based buckets reduces ranking costs and cache misses enough to offset any overhead, and that the two tailored re-ranking algorithms accelerate re-ranking across different quantization methods without harming accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BBC improves large-k ANN efficiency via bucketed candidate buffers and optimized re-ranking, delivering up to 3.8x speedup at recall@k=0.95.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A bucket-based collector organizes ANN candidates by distance to speed up large-k queries in quantization indexes by up to 3.8 times.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e13f9ba11c2bd7e3f8590534506c1625c4b92b3178cf6424f6073522005c47bd"},"source":{"id":"2604.01960","kind":"arxiv","version":3},"verdict":{"id":"561a2c56-bbd9-4e96-a68a-b8b001f54b24","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T20:43:39.806837Z","strongest_claim":"BBC accelerates existing quantization-based ANN methods by up to 3.8x at recall@k = 0.95 for large-k ANN queries.","one_line_summary":"BBC improves large-k ANN efficiency via bucketed candidate buffers and optimized re-ranking, delivering up to 3.8x speedup at recall@k=0.95.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That organizing candidates into distance-based buckets reduces ranking costs and cache misses enough to offset any overhead, and that the two tailored re-ranking algorithms accelerate re-ranking across different quantization methods without harming accuracy.","pith_extraction_headline":"A bucket-based collector organizes ANN candidates by distance to speed up large-k queries in quantization indexes by up to 3.8 times."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.01960/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":2,"snapshot_sha256":"531dac0ff0d37ee7290368daa2677776a1c17856a41bb76dc41e2e4c47b471d7"},"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":"2604.01960","created_at":"2026-06-03T01:05:12.435360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.01960v3","created_at":"2026-06-03T01:05:12.435360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01960","created_at":"2026-06-03T01:05:12.435360+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWGQFLBN273C","created_at":"2026-06-03T01:05:12.435360+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWGQFLBN273CPKSD","created_at":"2026-06-03T01:05:12.435360+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWGQFLBN","created_at":"2026-06-03T01:05:12.435360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.01960","citing_title":"BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB","json":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB.json","graph_json":"https://pith.science/api/pith-number/HWGQFLBN273CPKSDZF2DDEYGUB/graph.json","events_json":"https://pith.science/api/pith-number/HWGQFLBN273CPKSDZF2DDEYGUB/events.json","paper":"https://pith.science/paper/HWGQFLBN"},"agent_actions":{"view_html":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB","download_json":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB.json","view_paper":"https://pith.science/paper/HWGQFLBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.01960&json=true","fetch_graph":"https://pith.science/api/pith-number/HWGQFLBN273CPKSDZF2DDEYGUB/graph.json","fetch_events":"https://pith.science/api/pith-number/HWGQFLBN273CPKSDZF2DDEYGUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/action/storage_attestation","attest_author":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/action/author_attestation","sign_citation":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/action/citation_signature","submit_replication":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/action/replication_record"}},"created_at":"2026-06-03T01:05:12.435360+00:00","updated_at":"2026-06-03T01:05:12.435360+00:00"}