{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ML46U7NIQA6PALJGVNCA4MN4LY","short_pith_number":"pith:ML46U7NI","schema_version":"1.0","canonical_sha256":"62f9ea7da8803cf02d26ab440e31bc5e2c8a1835e0cb5f8be4ee4e6ede4b7380","source":{"kind":"arxiv","id":"2502.15182","version":1},"attestation_state":"computed","paper":{"title":"LEDD: Large Language Model-Empowered Data Discovery in Data Lakes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Chihua Ying, Jianmin Wang, Manwei Zhang, Qi An, Yihao Xu, Yuqing Zhu","submitted_at":"2025-02-21T03:30:43Z","abstract_excerpt":"Data discovery in data lakes with ever increasing datasets has long been recognized as a big challenge in the realm of data management, especially for semantic search of and hierarchical global catalog generation of tables. While large language models (LLMs) facilitate the processing of data semantics, challenges remain in architecting an end-to-end system that comprehensively exploits LLMs for the two semantics-related tasks. In this demo, we propose LEDD, an end-to-end system with an extensible architecture that leverages LLMs to provide hierarchical global catalogs with semantic meanings an"},"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":"2502.15182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-21T03:30:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"713c19b7a2ea0bf538a7fcc6ddb731b447da64a83bf071d6b7fd117f5a649cdc","abstract_canon_sha256":"692e86993879a029bc411ae73080efad13188092b5bb47d13493f75516344673"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:57.450846Z","signature_b64":"IKe1pNorWcdqxSf6tWKPNWLsrFeTB8Q97IAoCFYLEs6XMqcJsGub7MVctfCtoUvlqjwqAcl0BTYWdGMPxx7dDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f9ea7da8803cf02d26ab440e31bc5e2c8a1835e0cb5f8be4ee4e6ede4b7380","last_reissued_at":"2026-07-05T10:17:57.450363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:57.450363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEDD: Large Language Model-Empowered Data Discovery in Data Lakes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Chihua Ying, Jianmin Wang, Manwei Zhang, Qi An, Yihao Xu, Yuqing Zhu","submitted_at":"2025-02-21T03:30:43Z","abstract_excerpt":"Data discovery in data lakes with ever increasing datasets has long been recognized as a big challenge in the realm of data management, especially for semantic search of and hierarchical global catalog generation of tables. While large language models (LLMs) facilitate the processing of data semantics, challenges remain in architecting an end-to-end system that comprehensively exploits LLMs for the two semantics-related tasks. In this demo, we propose LEDD, an end-to-end system with an extensible architecture that leverages LLMs to provide hierarchical global catalogs with semantic meanings an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15182","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/2502.15182/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":"2502.15182","created_at":"2026-07-05T10:17:57.450417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15182v1","created_at":"2026-07-05T10:17:57.450417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15182","created_at":"2026-07-05T10:17:57.450417+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML46U7NIQA6P","created_at":"2026-07-05T10:17:57.450417+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML46U7NIQA6PALJG","created_at":"2026-07-05T10:17:57.450417+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML46U7NI","created_at":"2026-07-05T10:17:57.450417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY","json":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY.json","graph_json":"https://pith.science/api/pith-number/ML46U7NIQA6PALJGVNCA4MN4LY/graph.json","events_json":"https://pith.science/api/pith-number/ML46U7NIQA6PALJGVNCA4MN4LY/events.json","paper":"https://pith.science/paper/ML46U7NI"},"agent_actions":{"view_html":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY","download_json":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY.json","view_paper":"https://pith.science/paper/ML46U7NI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15182&json=true","fetch_graph":"https://pith.science/api/pith-number/ML46U7NIQA6PALJGVNCA4MN4LY/graph.json","fetch_events":"https://pith.science/api/pith-number/ML46U7NIQA6PALJGVNCA4MN4LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY/action/storage_attestation","attest_author":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY/action/author_attestation","sign_citation":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY/action/citation_signature","submit_replication":"https://pith.science/pith/ML46U7NIQA6PALJGVNCA4MN4LY/action/replication_record"}},"created_at":"2026-07-05T10:17:57.450417+00:00","updated_at":"2026-07-05T10:17:57.450417+00:00"}