{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BP3U2WLUPAJWFV5GPPJATMGHC2","short_pith_number":"pith:BP3U2WLU","schema_version":"1.0","canonical_sha256":"0bf74d5974781362d7a67bd209b0c7169e2344f8c88d6b9245ef8ff5e40d9f92","source":{"kind":"arxiv","id":"2409.16576","version":1},"attestation_state":"computed","paper":{"title":"FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.OS"],"primary_cat":"cs.IR","authors_text":"Bing Tian, Haikun Liu, Junhua Zhu, Shihai Xiao, Xiaofei Liao, Xuecang Zhang, Yuhang Tang, Yu Zhang, Zhuohui Duan","submitted_at":"2024-09-25T03:14:01Z","abstract_excerpt":"Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. We present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O o"},"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":"2409.16576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-09-25T03:14:01Z","cross_cats_sorted":["cs.DB","cs.OS"],"title_canon_sha256":"699e9925cd79e7fc311a9b5dbd85e5ed28ce5fe60bd2dbfee52d8fbdb4dc231c","abstract_canon_sha256":"6542f850952c1d10c57b37fd0ff2f73b4dc44f858fe38d13586e5f1e3588f5c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:23.162539Z","signature_b64":"0K3uwJVyQddyn/zYG0RZGq4dvWGaWce9MwpiSepnnz+qGIE7BV6sUydsocxgW3vY4OyWhDLomFRCzDj78aJcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf74d5974781362d7a67bd209b0c7169e2344f8c88d6b9245ef8ff5e40d9f92","last_reissued_at":"2026-07-05T09:14:23.162125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:23.162125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.OS"],"primary_cat":"cs.IR","authors_text":"Bing Tian, Haikun Liu, Junhua Zhu, Shihai Xiao, Xiaofei Liao, Xuecang Zhang, Yuhang Tang, Yu Zhang, Zhuohui Duan","submitted_at":"2024-09-25T03:14:01Z","abstract_excerpt":"Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. We present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16576","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.16576/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":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":"2409.16576","created_at":"2026-07-05T09:14:23.162185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16576v1","created_at":"2026-07-05T09:14:23.162185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16576","created_at":"2026-07-05T09:14:23.162185+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP3U2WLUPAJW","created_at":"2026-07-05T09:14:23.162185+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP3U2WLUPAJWFV5G","created_at":"2026-07-05T09:14:23.162185+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP3U2WLU","created_at":"2026-07-05T09:14:23.162185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25522","citing_title":"Co-Designing Graph-based Approximate Nearest Neighbor Search at Billion Scale for Processing-in-Memory","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2","json":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2.json","graph_json":"https://pith.science/api/pith-number/BP3U2WLUPAJWFV5GPPJATMGHC2/graph.json","events_json":"https://pith.science/api/pith-number/BP3U2WLUPAJWFV5GPPJATMGHC2/events.json","paper":"https://pith.science/paper/BP3U2WLU"},"agent_actions":{"view_html":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2","download_json":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2.json","view_paper":"https://pith.science/paper/BP3U2WLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16576&json=true","fetch_graph":"https://pith.science/api/pith-number/BP3U2WLUPAJWFV5GPPJATMGHC2/graph.json","fetch_events":"https://pith.science/api/pith-number/BP3U2WLUPAJWFV5GPPJATMGHC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2/action/storage_attestation","attest_author":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2/action/author_attestation","sign_citation":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2/action/citation_signature","submit_replication":"https://pith.science/pith/BP3U2WLUPAJWFV5GPPJATMGHC2/action/replication_record"}},"created_at":"2026-07-05T09:14:23.162185+00:00","updated_at":"2026-07-05T09:14:23.162185+00:00"}