{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HWGQFLBN273CPKSDZF2DDEYGUB","short_pith_number":"pith:HWGQFLBN","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"},"canonical_sha256":"3d8d02ac2dd7f627aa43c974319306a05afc69ae19fec5df9608662f9bc63f8a","source":{"kind":"arxiv","id":"2604.01960","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.01960","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2604.01960v3","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01960","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"HWGQFLBN273C","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"HWGQFLBN273CPKSD","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"HWGQFLBN","created_at":"2026-06-03T01:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HWGQFLBN273CPKSDZF2DDEYGUB","target":"record","payload":{"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"},"canonical_sha256":"3d8d02ac2dd7f627aa43c974319306a05afc69ae19fec5df9608662f9bc63f8a","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"},"source_kind":"arxiv","source_id":"2604.01960","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7Isy+DXo83Cc0wTk2Sblh41VEuMs44A5o3wyEQ84D3eAYE95tTSBDgvDcDbS2olTU7BAtICkCw4dPR/NNdsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T08:17:04.691905Z"},"content_sha256":"6399e48b0834323a62797abf73f523e9461ecc74a011ba6fc78ba468e4206a3d","schema_version":"1.0","event_id":"sha256:6399e48b0834323a62797abf73f523e9461ecc74a011ba6fc78ba468e4206a3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HWGQFLBN273CPKSDZF2DDEYGUB","target":"graph","payload":{"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"},"verdict_id":"561a2c56-bbd9-4e96-a68a-b8b001f54b24"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ikJVy54jRPe19FlNEUf7ORtVXA6+tn6ekJDKgevamXC7ZxyR68LaI1WU/esEgjrK+ZGfKdfG0vTTr5AgHLb8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T08:17:04.692388Z"},"content_sha256":"0e763531a0a04e682a19540dc449dcd873b31e4d85ab1039dfeed4470d30015d","schema_version":"1.0","event_id":"sha256:0e763531a0a04e682a19540dc449dcd873b31e4d85ab1039dfeed4470d30015d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/bundle.json","state_url":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWGQFLBN273CPKSDZF2DDEYGUB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-03T08:17:04Z","links":{"resolver":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB","bundle":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/bundle.json","state":"https://pith.science/pith/HWGQFLBN273CPKSDZF2DDEYGUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWGQFLBN273CPKSDZF2DDEYGUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HWGQFLBN273CPKSDZF2DDEYGUB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9833e17833692bf0d9b2f0e01c5d7c410e2610b587677ef7a07ac6b6f53216ae","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-04-02T12:22:38Z","title_canon_sha256":"60bab5b969a9b1453a4475c9b077b702d588c19ffa20fc516e462ff9be81bf86"},"schema_version":"1.0","source":{"id":"2604.01960","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.01960","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2604.01960v3","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01960","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"HWGQFLBN273C","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"HWGQFLBN273CPKSD","created_at":"2026-06-03T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"HWGQFLBN","created_at":"2026-06-03T01:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:0e763531a0a04e682a19540dc449dcd873b31e4d85ab1039dfeed4470d30015d","target":"graph","created_at":"2026-06-03T01:05:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"BBC accelerates existing quantization-based ANN methods by up to 3.8x at recall@k = 0.95 for large-k ANN queries."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"e13f9ba11c2bd7e3f8590534506c1625c4b92b3178cf6424f6073522005c47bd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"531dac0ff0d37ee7290368daa2677776a1c17856a41bb76dc41e2e4c47b471d7"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.01960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Bin Cui, Gao Cong, Jinwei Zhu, Kai Zeng, Ziqi Yin","cross_cats":["cs.DS"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-04-02T12:22:38Z","title":"BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01960","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-13T20:43:39.806837Z","id":"561a2c56-bbd9-4e96-a68a-b8b001f54b24","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"BBC accelerates existing quantization-based ANN methods by up to 3.8x at recall@k = 0.95 for large-k ANN queries.","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."}},"verdict_id":"561a2c56-bbd9-4e96-a68a-b8b001f54b24"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6399e48b0834323a62797abf73f523e9461ecc74a011ba6fc78ba468e4206a3d","target":"record","created_at":"2026-06-03T01:05:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9833e17833692bf0d9b2f0e01c5d7c410e2610b587677ef7a07ac6b6f53216ae","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-04-02T12:22:38Z","title_canon_sha256":"60bab5b969a9b1453a4475c9b077b702d588c19ffa20fc516e462ff9be81bf86"},"schema_version":"1.0","source":{"id":"2604.01960","kind":"arxiv","version":3}},"canonical_sha256":"3d8d02ac2dd7f627aa43c974319306a05afc69ae19fec5df9608662f9bc63f8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d8d02ac2dd7f627aa43c974319306a05afc69ae19fec5df9608662f9bc63f8a","first_computed_at":"2026-06-03T01:05:12.435297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:12.435297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R/w2kTcOgikoeka9jO+ZDJM5cFAWZYhykaL39PTyXRkjv6s1uQFwe4pihhOhUPnPmvIpnBWW0EcAAgt3LsfKBg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:12.435831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.01960","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6399e48b0834323a62797abf73f523e9461ecc74a011ba6fc78ba468e4206a3d","sha256:0e763531a0a04e682a19540dc449dcd873b31e4d85ab1039dfeed4470d30015d"],"state_sha256":"8bd81ef18df87eb72a2493cee9d69a23f0ee5e41fcff54d83e9ab2a6f5f29719"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfvPRV9AWXlB5UJYpOw7Qgd/buPo4kdH9uYyZKJbzTaxMSEvCDepc6cFaT6U9hSjYg2mzxUvDK+3o0yyEsFICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T08:17:04.694798Z","bundle_sha256":"7270b47484c3be614a508ab03fbca2ca2cc133b7f634a09b5f7b1ad2d3cb1006"}}