{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQOUDQOT75GYVMLS3AYSDMSMDY","short_pith_number":"pith:BQOUDQOT","schema_version":"1.0","canonical_sha256":"0c1d41c1d3ff4d8ab172d83121b24c1e3e38b857baf6096c66360a6395f03b44","source":{"kind":"arxiv","id":"2410.23805","version":2},"attestation_state":"computed","paper":{"title":"UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Amelie Chi Zhou, Sitian Chen, Xin Yao, Yucheng Shi, Yusen Li","submitted_at":"2024-10-31T10:45:02Z","abstract_excerpt":"Approximate Nearest Neighbor Search (ANNS) is a critical component of modern AI systems, such as recommendation engines and retrieval-augmented large language models (RAG-LLMs). However, scaling ANNS to billion-entry datasets exposes critical inefficiencies: CPU-based solutions are bottlenecked by memory bandwidth limitations, while GPU implementations underutilize hardware resources, leading to suboptimal performance and energy consumption. To address these challenges, we introduce \\emph{UpANNS}, a novel framework leveraging Processing-in-Memory (PIM) architecture to accelerate billion-scale "},"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":"2410.23805","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-10-31T10:45:02Z","cross_cats_sorted":[],"title_canon_sha256":"f102434e72a7bf6af5c1923430fc079bc2eb5b7ce6d9ccd2b2352bd0e7a17d3c","abstract_canon_sha256":"1bba63836755b75ae053fdea322e3a321d6fc56e682e6bf0ac2e40c4bfbd3a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:16.035623Z","signature_b64":"dscfAf4UYoODemRhuHB7gv6PKPnZdTTNBr5J1CszCbYzwC1mk5aBym2l9GK2EF6XZpPp1J+wkP13692ASBOyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1d41c1d3ff4d8ab172d83121b24c1e3e38b857baf6096c66360a6395f03b44","last_reissued_at":"2026-07-05T11:56:16.035089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:16.035089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Amelie Chi Zhou, Sitian Chen, Xin Yao, Yucheng Shi, Yusen Li","submitted_at":"2024-10-31T10:45:02Z","abstract_excerpt":"Approximate Nearest Neighbor Search (ANNS) is a critical component of modern AI systems, such as recommendation engines and retrieval-augmented large language models (RAG-LLMs). However, scaling ANNS to billion-entry datasets exposes critical inefficiencies: CPU-based solutions are bottlenecked by memory bandwidth limitations, while GPU implementations underutilize hardware resources, leading to suboptimal performance and energy consumption. To address these challenges, we introduce \\emph{UpANNS}, a novel framework leveraging Processing-in-Memory (PIM) architecture to accelerate billion-scale "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23805","kind":"arxiv","version":2},"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/2410.23805/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":"2410.23805","created_at":"2026-07-05T11:56:16.035154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23805v2","created_at":"2026-07-05T11:56:16.035154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23805","created_at":"2026-07-05T11:56:16.035154+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQOUDQOT75GY","created_at":"2026-07-05T11:56:16.035154+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQOUDQOT75GYVMLS","created_at":"2026-07-05T11:56:16.035154+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQOUDQOT","created_at":"2026-07-05T11:56:16.035154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10135","citing_title":"ScaleGANN: Accelerate Large-Scale ANN Indexing by Cost-effective Cloud GPUs","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY","json":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY.json","graph_json":"https://pith.science/api/pith-number/BQOUDQOT75GYVMLS3AYSDMSMDY/graph.json","events_json":"https://pith.science/api/pith-number/BQOUDQOT75GYVMLS3AYSDMSMDY/events.json","paper":"https://pith.science/paper/BQOUDQOT"},"agent_actions":{"view_html":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY","download_json":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY.json","view_paper":"https://pith.science/paper/BQOUDQOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23805&json=true","fetch_graph":"https://pith.science/api/pith-number/BQOUDQOT75GYVMLS3AYSDMSMDY/graph.json","fetch_events":"https://pith.science/api/pith-number/BQOUDQOT75GYVMLS3AYSDMSMDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY/action/storage_attestation","attest_author":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY/action/author_attestation","sign_citation":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY/action/citation_signature","submit_replication":"https://pith.science/pith/BQOUDQOT75GYVMLS3AYSDMSMDY/action/replication_record"}},"created_at":"2026-07-05T11:56:16.035154+00:00","updated_at":"2026-07-05T11:56:16.035154+00:00"}