{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J6UCXT2KIKDHK5B35MZU3LTIA7","short_pith_number":"pith:J6UCXT2K","schema_version":"1.0","canonical_sha256":"4fa82bcf4a428675743beb334dae6807e110c78ad9d0b07e42456fc2673efeae","source":{"kind":"arxiv","id":"2402.02643","version":1},"attestation_state":"computed","paper":{"title":"LLM-Enhanced Data Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Guoliang Li, Xinyang Zhao, Xuanhe Zhou","submitted_at":"2024-02-04T23:42:02Z","abstract_excerpt":"Machine learning (ML) techniques for optimizing data management problems have been extensively studied and widely deployed in recent five years. However traditional ML methods have limitations on generalizability (adapting to different scenarios) and inference ability (understanding the context). Fortunately, large language models (LLMs) have shown high generalizability and human-competitive abilities in understanding context, which are promising for data management tasks (e.g., database diagnosis, database tuning). However, existing LLMs have several limitations: hallucination, high cost, and"},"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":"2402.02643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-04T23:42:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"8d885002339994456577e4648201de89c98187b1769507a0f699650131e47502","abstract_canon_sha256":"652bef06be107a92c2e0275b45ca99e63e94ad7eab6b6a543f866ed7de02394d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:16.745696Z","signature_b64":"VFBuch7SlOmg2Fh6YoA7xwmAn02lqFrPEnD64CAjQC5cOqdN2ud3R5DT0LW7Qw5edhtF8hX6ZnrZfA4j6Fj2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa82bcf4a428675743beb334dae6807e110c78ad9d0b07e42456fc2673efeae","last_reissued_at":"2026-07-05T07:41:16.745291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:16.745291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Enhanced Data Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Guoliang Li, Xinyang Zhao, Xuanhe Zhou","submitted_at":"2024-02-04T23:42:02Z","abstract_excerpt":"Machine learning (ML) techniques for optimizing data management problems have been extensively studied and widely deployed in recent five years. However traditional ML methods have limitations on generalizability (adapting to different scenarios) and inference ability (understanding the context). Fortunately, large language models (LLMs) have shown high generalizability and human-competitive abilities in understanding context, which are promising for data management tasks (e.g., database diagnosis, database tuning). However, existing LLMs have several limitations: hallucination, high cost, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02643","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/2402.02643/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":"2402.02643","created_at":"2026-07-05T07:41:16.745360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02643v1","created_at":"2026-07-05T07:41:16.745360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02643","created_at":"2026-07-05T07:41:16.745360+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6UCXT2KIKDH","created_at":"2026-07-05T07:41:16.745360+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6UCXT2KIKDHK5B3","created_at":"2026-07-05T07:41:16.745360+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6UCXT2K","created_at":"2026-07-05T07:41:16.745360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09611","citing_title":"Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02861","citing_title":"LLM+Graph@VLDB'2025 Workshop Summary","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00043","citing_title":"SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7","json":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7.json","graph_json":"https://pith.science/api/pith-number/J6UCXT2KIKDHK5B35MZU3LTIA7/graph.json","events_json":"https://pith.science/api/pith-number/J6UCXT2KIKDHK5B35MZU3LTIA7/events.json","paper":"https://pith.science/paper/J6UCXT2K"},"agent_actions":{"view_html":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7","download_json":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7.json","view_paper":"https://pith.science/paper/J6UCXT2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02643&json=true","fetch_graph":"https://pith.science/api/pith-number/J6UCXT2KIKDHK5B35MZU3LTIA7/graph.json","fetch_events":"https://pith.science/api/pith-number/J6UCXT2KIKDHK5B35MZU3LTIA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7/action/storage_attestation","attest_author":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7/action/author_attestation","sign_citation":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7/action/citation_signature","submit_replication":"https://pith.science/pith/J6UCXT2KIKDHK5B35MZU3LTIA7/action/replication_record"}},"created_at":"2026-07-05T07:41:16.745360+00:00","updated_at":"2026-07-05T07:41:16.745360+00:00"}