{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LF5ZXTFWN5WYQOIYBNUA6IMZDQ","short_pith_number":"pith:LF5ZXTFW","schema_version":"1.0","canonical_sha256":"597b9bccb66f6d8839180b680f21991c237ffcbfb683d23cf9fa6f805b159d86","source":{"kind":"arxiv","id":"2312.03141","version":2},"attestation_state":"computed","paper":{"title":"NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Andrew Chang, Hai \"Helen\" Li, Linghao Song, Qilin Zheng, Shiyu Li, Yiran Chen, Yitu Wang, Zongwang Li","submitted_at":"2023-12-05T21:21:01Z","abstract_excerpt":"Approximate nearest neighbor search (ANNS) is a key retrieval technique for vector database and many data center applications, such as person re-identification and recommendation systems. It is also fundamental to retrieval augmented generation (RAG) for large language models (LLM) now. Among all the ANNS algorithms, graph-traversal-based ANNS achieves the highest recall rate. However, as the size of dataset increases, the graph may require hundreds of gigabytes of memory, exceeding the main memory capacity of a single workstation node. Although we can do partitioning and use solid-state drive"},"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":"2312.03141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2023-12-05T21:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"54e1902fe2499d749cd7c8e2d98f4995963ce59237b3441540a7fa55822e7c20","abstract_canon_sha256":"6f9724d3f81edf3fd8ca872d53183164f19c03e85565900a59c510dc886ddde2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:23.383691Z","signature_b64":"TMKwObULRnfgxpUs7AtEMzx+Dd0sl73Fd291bLapHbf66uHJ8oQqsqWkidV1C0BHBctInL9pq6E7DYUbnP9WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"597b9bccb66f6d8839180b680f21991c237ffcbfb683d23cf9fa6f805b159d86","last_reissued_at":"2026-07-05T08:24:23.383204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:23.383204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Andrew Chang, Hai \"Helen\" Li, Linghao Song, Qilin Zheng, Shiyu Li, Yiran Chen, Yitu Wang, Zongwang Li","submitted_at":"2023-12-05T21:21:01Z","abstract_excerpt":"Approximate nearest neighbor search (ANNS) is a key retrieval technique for vector database and many data center applications, such as person re-identification and recommendation systems. It is also fundamental to retrieval augmented generation (RAG) for large language models (LLM) now. Among all the ANNS algorithms, graph-traversal-based ANNS achieves the highest recall rate. However, as the size of dataset increases, the graph may require hundreds of gigabytes of memory, exceeding the main memory capacity of a single workstation node. Although we can do partitioning and use solid-state drive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03141","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/2312.03141/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":"2312.03141","created_at":"2026-07-05T08:24:23.383265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03141v2","created_at":"2026-07-05T08:24:23.383265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03141","created_at":"2026-07-05T08:24:23.383265+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF5ZXTFWN5WY","created_at":"2026-07-05T08:24:23.383265+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF5ZXTFWN5WYQOIY","created_at":"2026-07-05T08:24:23.383265+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF5ZXTFW","created_at":"2026-07-05T08:24:23.383265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15246","citing_title":"Accelerating Retrieval-Augmented Generation","ref_index":108,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ","json":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ.json","graph_json":"https://pith.science/api/pith-number/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/graph.json","events_json":"https://pith.science/api/pith-number/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/events.json","paper":"https://pith.science/paper/LF5ZXTFW"},"agent_actions":{"view_html":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ","download_json":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ.json","view_paper":"https://pith.science/paper/LF5ZXTFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03141&json=true","fetch_graph":"https://pith.science/api/pith-number/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/action/storage_attestation","attest_author":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/action/author_attestation","sign_citation":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/action/citation_signature","submit_replication":"https://pith.science/pith/LF5ZXTFWN5WYQOIYBNUA6IMZDQ/action/replication_record"}},"created_at":"2026-07-05T08:24:23.383265+00:00","updated_at":"2026-07-05T08:24:23.383265+00:00"}