{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BRMIIGMF73RWMV3WPQHVVMTAHA","short_pith_number":"pith:BRMIIGMF","schema_version":"1.0","canonical_sha256":"0c58841985fee36657767c0f5ab260381892fb22cf4d6a40e8e320c384bc0004","source":{"kind":"arxiv","id":"2503.02240","version":2},"attestation_state":"computed","paper":{"title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Cuiping Li, Fuxin Jiang, Haoyang Li, Hong Chen, Jianjun Chen, Jing Zhang, Rui Shi, Shang Wu, Shuai Wang, Tieying Zhang, Xiaokang Zhang, Xinmei Huang","submitted_at":"2025-03-04T03:30:56Z","abstract_excerpt":"Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases. While recent advancements in large language models (LLMs) have significantly enhanced text-to-SQL performance, existing approaches face notable limitations in real-world text-to-SQL applications. Prompting-based methods often depend on closed-source LLMs, which are expensive, raise privacy concerns, and lack customization. Fine-tuning-based methods, on the other hand, suffer from poor generalizability due to the limited coverage of publicly "},"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":"2503.02240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T03:30:56Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"0b6e53ba549854a2461003ab9f0d49b1b97feb4f62863e12d0791c1cd4a84e0b","abstract_canon_sha256":"a3bf42728b189d91f28e6b581cf827b7c9dd92408325db36fdb3cb82ccc23b5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:29.026986Z","signature_b64":"TR9RMf1eM3TvbU4Z8nsbNkLarpHHV8h/PRMt7/KemFdDa5x5qQBUh17fgwyjDANvHZhrIn8Hjc41SJ5mgDiyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c58841985fee36657767c0f5ab260381892fb22cf4d6a40e8e320c384bc0004","last_reissued_at":"2026-07-05T11:36:29.026487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:29.026487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Cuiping Li, Fuxin Jiang, Haoyang Li, Hong Chen, Jianjun Chen, Jing Zhang, Rui Shi, Shang Wu, Shuai Wang, Tieying Zhang, Xiaokang Zhang, Xinmei Huang","submitted_at":"2025-03-04T03:30:56Z","abstract_excerpt":"Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases. While recent advancements in large language models (LLMs) have significantly enhanced text-to-SQL performance, existing approaches face notable limitations in real-world text-to-SQL applications. Prompting-based methods often depend on closed-source LLMs, which are expensive, raise privacy concerns, and lack customization. Fine-tuning-based methods, on the other hand, suffer from poor generalizability due to the limited coverage of publicly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02240","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/2503.02240/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":"2503.02240","created_at":"2026-07-05T11:36:29.026533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02240v2","created_at":"2026-07-05T11:36:29.026533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02240","created_at":"2026-07-05T11:36:29.026533+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRMIIGMF73RW","created_at":"2026-07-05T11:36:29.026533+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRMIIGMF73RWMV3W","created_at":"2026-07-05T11:36:29.026533+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRMIIGMF","created_at":"2026-07-05T11:36:29.026533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26613","citing_title":"EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05906","citing_title":"ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23693","citing_title":"EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04334","citing_title":"SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12319","citing_title":"Data-aware candidate selection in NL2SQL translation via small separating instances","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03465","citing_title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA","json":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA.json","graph_json":"https://pith.science/api/pith-number/BRMIIGMF73RWMV3WPQHVVMTAHA/graph.json","events_json":"https://pith.science/api/pith-number/BRMIIGMF73RWMV3WPQHVVMTAHA/events.json","paper":"https://pith.science/paper/BRMIIGMF"},"agent_actions":{"view_html":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA","download_json":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA.json","view_paper":"https://pith.science/paper/BRMIIGMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02240&json=true","fetch_graph":"https://pith.science/api/pith-number/BRMIIGMF73RWMV3WPQHVVMTAHA/graph.json","fetch_events":"https://pith.science/api/pith-number/BRMIIGMF73RWMV3WPQHVVMTAHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA/action/storage_attestation","attest_author":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA/action/author_attestation","sign_citation":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA/action/citation_signature","submit_replication":"https://pith.science/pith/BRMIIGMF73RWMV3WPQHVVMTAHA/action/replication_record"}},"created_at":"2026-07-05T11:36:29.026533+00:00","updated_at":"2026-07-05T11:36:29.026533+00:00"}