{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4UIM3NAWUDWZK7PZZVQQQLPH5P","short_pith_number":"pith:4UIM3NAW","schema_version":"1.0","canonical_sha256":"e510cdb416a0ed957df9cd61082de7ebfa4e6eafbde2e08245b663ebef110804","source":{"kind":"arxiv","id":"2402.01763","version":4},"attestation_state":"computed","paper":{"title":"When Large Language Models Meet Vector Databases: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Bo Yuan, Chunjiang Liu, Haiyun Xu, Kehai Chen, Min Zhang, Yikun Han, Yongye Su, Zhi Jing","submitted_at":"2024-01-30T23:35:28Z","abstract_excerpt":"This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area. With the proliferation of LLMs comes a host of challenges, including hallucinations, outdated knowledge, prohibitive commercial application costs, and memory issues. VecDBs emerge as a compelling solution to these issues by offering an efficient means to store, retrieve, and manage the high-dimensional vector representations intrinsic to LLM operations. Through this nuanced review, we delineate the foundational principles of LLMs and Vec"},"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":"2402.01763","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-01-30T23:35:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b15073c74d1cb0b3467aea5ee6eb4bce4a9c5a22e5a27828d2fa9b95196b50ae","abstract_canon_sha256":"4542ee98e0e8fe03f92aab18715f6d33a2970fb3646f0d55ad79e69c3945285b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:37.657578Z","signature_b64":"e1xQDLymeIyKFcdz9TuTy6ijwrK/OQcj+RFA5p9iC4MX2tyDY4w6/TR5FyyMbxxMYRmdu4WGrKfmWEAPQRyiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e510cdb416a0ed957df9cd61082de7ebfa4e6eafbde2e08245b663ebef110804","last_reissued_at":"2026-07-05T11:25:37.657072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:37.657072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Large Language Models Meet Vector Databases: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Bo Yuan, Chunjiang Liu, Haiyun Xu, Kehai Chen, Min Zhang, Yikun Han, Yongye Su, Zhi Jing","submitted_at":"2024-01-30T23:35:28Z","abstract_excerpt":"This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area. With the proliferation of LLMs comes a host of challenges, including hallucinations, outdated knowledge, prohibitive commercial application costs, and memory issues. VecDBs emerge as a compelling solution to these issues by offering an efficient means to store, retrieve, and manage the high-dimensional vector representations intrinsic to LLM operations. Through this nuanced review, we delineate the foundational principles of LLMs and Vec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01763","kind":"arxiv","version":4},"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/2402.01763/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":"2402.01763","created_at":"2026-07-05T11:25:37.657130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01763v4","created_at":"2026-07-05T11:25:37.657130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01763","created_at":"2026-07-05T11:25:37.657130+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UIM3NAWUDWZ","created_at":"2026-07-05T11:25:37.657130+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UIM3NAWUDWZK7PZ","created_at":"2026-07-05T11:25:37.657130+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UIM3NAW","created_at":"2026-07-05T11:25:37.657130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27445","citing_title":"RAGe: A Retrieval-Augmented Generation Evaluation Framework","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20018","citing_title":"MINT: Multi-Vector Search Index Tuning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25401","citing_title":"DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P","json":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P.json","graph_json":"https://pith.science/api/pith-number/4UIM3NAWUDWZK7PZZVQQQLPH5P/graph.json","events_json":"https://pith.science/api/pith-number/4UIM3NAWUDWZK7PZZVQQQLPH5P/events.json","paper":"https://pith.science/paper/4UIM3NAW"},"agent_actions":{"view_html":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P","download_json":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P.json","view_paper":"https://pith.science/paper/4UIM3NAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01763&json=true","fetch_graph":"https://pith.science/api/pith-number/4UIM3NAWUDWZK7PZZVQQQLPH5P/graph.json","fetch_events":"https://pith.science/api/pith-number/4UIM3NAWUDWZK7PZZVQQQLPH5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P/action/storage_attestation","attest_author":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P/action/author_attestation","sign_citation":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P/action/citation_signature","submit_replication":"https://pith.science/pith/4UIM3NAWUDWZK7PZZVQQQLPH5P/action/replication_record"}},"created_at":"2026-07-05T11:25:37.657130+00:00","updated_at":"2026-07-05T11:25:37.657130+00:00"}