{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RFDYEU6Q24KFMSUR5PO3L7INUM","short_pith_number":"pith:RFDYEU6Q","schema_version":"1.0","canonical_sha256":"89478253d0d714564a91ebddb5fd0da3157df1d1efad1096badbeb9ce6e1bbac","source":{"kind":"arxiv","id":"2504.14837","version":5},"attestation_state":"computed","paper":{"title":"SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Huaizhong Liu, Jiahui Li, Tongwang Wu, Yajie Feng, Yunjun Gao, Yuren Mao","submitted_at":"2025-04-21T03:37:43Z","abstract_excerpt":"High quality SQL corpus is essential for intelligent database. For example, Text-to-SQL requires SQL queries and correspond natural language questions as training samples. However, collecting such query corpus remains challenging in practice due to the high cost of manual annotation, which highlights the importance of automatic SQL generation. Despite recent advances, existing generation methods still face limitations in achieving both diversity and cost-effectiveness. Besides, many methods also treat all tables equally, which overlooks schema complexity and leads to under-utilization of struc"},"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":"2504.14837","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-04-21T03:37:43Z","cross_cats_sorted":[],"title_canon_sha256":"cfec7242da2ab82e0b81eb007892eadc19774510ddc08a99cf6442740e27b82e","abstract_canon_sha256":"cf6391f6b1e1b60408efb5ae1b1502ea4cacaee5a99f3940b07222eedc6cb229"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:45.140034Z","signature_b64":"0moBEpid96WBntnuKGa4GsjuZRYy+2+mblBCzA7Lcb7Vydg/PRbZv6bQUTyQ//yVYqkF8QNpJ6bQnFe3F8X5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89478253d0d714564a91ebddb5fd0da3157df1d1efad1096badbeb9ce6e1bbac","last_reissued_at":"2026-07-05T12:02:45.139486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:45.139486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Huaizhong Liu, Jiahui Li, Tongwang Wu, Yajie Feng, Yunjun Gao, Yuren Mao","submitted_at":"2025-04-21T03:37:43Z","abstract_excerpt":"High quality SQL corpus is essential for intelligent database. For example, Text-to-SQL requires SQL queries and correspond natural language questions as training samples. However, collecting such query corpus remains challenging in practice due to the high cost of manual annotation, which highlights the importance of automatic SQL generation. Despite recent advances, existing generation methods still face limitations in achieving both diversity and cost-effectiveness. Besides, many methods also treat all tables equally, which overlooks schema complexity and leads to under-utilization of struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14837","kind":"arxiv","version":5},"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/2504.14837/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":"2504.14837","created_at":"2026-07-05T12:02:45.139551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14837v5","created_at":"2026-07-05T12:02:45.139551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14837","created_at":"2026-07-05T12:02:45.139551+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFDYEU6Q24KF","created_at":"2026-07-05T12:02:45.139551+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFDYEU6Q24KFMSUR","created_at":"2026-07-05T12:02:45.139551+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFDYEU6Q","created_at":"2026-07-05T12:02:45.139551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.23375","citing_title":"Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06804","citing_title":"LASER: A Data-Centric Method for Low-Cost and Efficient SQL Rewriting based on SQL-GRPO","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM","json":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM.json","graph_json":"https://pith.science/api/pith-number/RFDYEU6Q24KFMSUR5PO3L7INUM/graph.json","events_json":"https://pith.science/api/pith-number/RFDYEU6Q24KFMSUR5PO3L7INUM/events.json","paper":"https://pith.science/paper/RFDYEU6Q"},"agent_actions":{"view_html":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM","download_json":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM.json","view_paper":"https://pith.science/paper/RFDYEU6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14837&json=true","fetch_graph":"https://pith.science/api/pith-number/RFDYEU6Q24KFMSUR5PO3L7INUM/graph.json","fetch_events":"https://pith.science/api/pith-number/RFDYEU6Q24KFMSUR5PO3L7INUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM/action/storage_attestation","attest_author":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM/action/author_attestation","sign_citation":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM/action/citation_signature","submit_replication":"https://pith.science/pith/RFDYEU6Q24KFMSUR5PO3L7INUM/action/replication_record"}},"created_at":"2026-07-05T12:02:45.139551+00:00","updated_at":"2026-07-05T12:02:45.139551+00:00"}