{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GE4TL2GMCCE7LKZLDAKKQR3V4C","short_pith_number":"pith:GE4TL2GM","schema_version":"1.0","canonical_sha256":"313935e8cc1089f5ab2b1814a84775e092575714572e7d2e5f51856f634b7772","source":{"kind":"arxiv","id":"2507.04687","version":2},"attestation_state":"computed","paper":{"title":"LAKEGEN: A LLM-based Tabular Corpus Generator for Evaluating Dataset Discovery in Data Lakes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Asterios Katsifodimos, Christos Faloutsos, Chuan Lei, Huzefa Rangwala, Xiao Qin, Zhenwei Dai","submitted_at":"2025-07-07T06:08:45Z","abstract_excerpt":"How to generate a large, realistic set of tables along with joinability relationships, to stress-test dataset discovery methods? Dataset discovery methods aim to automatically identify related data assets in a data lake. The development and evaluation of such solutions for customers from a wide range of business domains, relies on diverse, high quality and domain-specific tabular benchmarks. Large language models (LLMs) are trained on a wide variety of text data, which can provide a strong foundation of general and domain-specific knowledge. In this paper, we ask the question -- \\textit{can we"},"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":"2507.04687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-07T06:08:45Z","cross_cats_sorted":[],"title_canon_sha256":"5dead9e9a7908465dbca6bbe69859c030bafe7cb11d6bea71e8cede6aca2a3c1","abstract_canon_sha256":"60ed7488a7786bede74d72c12c4034a0a7b68a27052c610204f2f1927d29919a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:52.711760Z","signature_b64":"kmw67RCVW0W+3ZJa1VhufO+p0wrKZYv4rMELXvKpvNRX9ViVvgN2zfbk7ebQYUE6qxCziHZM9CXlRFb1XFJDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"313935e8cc1089f5ab2b1814a84775e092575714572e7d2e5f51856f634b7772","last_reissued_at":"2026-07-05T11:33:52.711183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:52.711183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAKEGEN: A LLM-based Tabular Corpus Generator for Evaluating Dataset Discovery in Data Lakes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Asterios Katsifodimos, Christos Faloutsos, Chuan Lei, Huzefa Rangwala, Xiao Qin, Zhenwei Dai","submitted_at":"2025-07-07T06:08:45Z","abstract_excerpt":"How to generate a large, realistic set of tables along with joinability relationships, to stress-test dataset discovery methods? Dataset discovery methods aim to automatically identify related data assets in a data lake. The development and evaluation of such solutions for customers from a wide range of business domains, relies on diverse, high quality and domain-specific tabular benchmarks. Large language models (LLMs) are trained on a wide variety of text data, which can provide a strong foundation of general and domain-specific knowledge. In this paper, we ask the question -- \\textit{can we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04687","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/2507.04687/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":"2507.04687","created_at":"2026-07-05T11:33:52.711249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04687v2","created_at":"2026-07-05T11:33:52.711249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04687","created_at":"2026-07-05T11:33:52.711249+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE4TL2GMCCE7","created_at":"2026-07-05T11:33:52.711249+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE4TL2GMCCE7LKZL","created_at":"2026-07-05T11:33:52.711249+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE4TL2GM","created_at":"2026-07-05T11:33:52.711249+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/GE4TL2GMCCE7LKZLDAKKQR3V4C","json":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C.json","graph_json":"https://pith.science/api/pith-number/GE4TL2GMCCE7LKZLDAKKQR3V4C/graph.json","events_json":"https://pith.science/api/pith-number/GE4TL2GMCCE7LKZLDAKKQR3V4C/events.json","paper":"https://pith.science/paper/GE4TL2GM"},"agent_actions":{"view_html":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C","download_json":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C.json","view_paper":"https://pith.science/paper/GE4TL2GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04687&json=true","fetch_graph":"https://pith.science/api/pith-number/GE4TL2GMCCE7LKZLDAKKQR3V4C/graph.json","fetch_events":"https://pith.science/api/pith-number/GE4TL2GMCCE7LKZLDAKKQR3V4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C/action/storage_attestation","attest_author":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C/action/author_attestation","sign_citation":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C/action/citation_signature","submit_replication":"https://pith.science/pith/GE4TL2GMCCE7LKZLDAKKQR3V4C/action/replication_record"}},"created_at":"2026-07-05T11:33:52.711249+00:00","updated_at":"2026-07-05T11:33:52.711249+00:00"}