{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G27DJKVDY3J42NCISGW74HKEQC","short_pith_number":"pith:G27DJKVD","schema_version":"1.0","canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","source":{"kind":"arxiv","id":"2503.04959","version":2},"attestation_state":"computed","paper":{"title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haolei Xu, Haoyuan Ma, Hengwei Liu, Jun Wang, Qiuying Peng, Weiming Lu, Wenqi Zhang, Yongliang Shen","submitted_at":"2025-03-06T20:46:43Z","abstract_excerpt":"Recent text-to-SQL systems powered by large language models (LLMs) have demonstrated remarkable performance in translating natural language queries into SQL. However, these systems often struggle with complex database structures and domain-specific queries, as they primarily focus on enhancing logical reasoning and SQL syntax while overlooking the critical need for comprehensive database understanding. To address this limitation, we propose DB-Explore, a novel framework that systematically aligns LLMs with database knowledge through automated exploration and instruction synthesis. DB-Explore c"},"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":"2503.04959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T20:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"c946044e59582d778aff1c4957517e8aa7b9816f7d6d64841230dd5ccf02974b","abstract_canon_sha256":"9eef8eeb38c6df998cfed1757039a5daf4b6c9b7a2d9314d4c8e814d46874ccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:29.224368Z","signature_b64":"kgYBd/o4/2so9uaCs8DwGdiAqe28gSQa09BobR4Pl7lgedWE52GntPG/AiUXSbNC09VhOd2vtLwQaJ5b/YCuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","last_reissued_at":"2026-07-05T11:06:29.223817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:29.223817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haolei Xu, Haoyuan Ma, Hengwei Liu, Jun Wang, Qiuying Peng, Weiming Lu, Wenqi Zhang, Yongliang Shen","submitted_at":"2025-03-06T20:46:43Z","abstract_excerpt":"Recent text-to-SQL systems powered by large language models (LLMs) have demonstrated remarkable performance in translating natural language queries into SQL. However, these systems often struggle with complex database structures and domain-specific queries, as they primarily focus on enhancing logical reasoning and SQL syntax while overlooking the critical need for comprehensive database understanding. To address this limitation, we propose DB-Explore, a novel framework that systematically aligns LLMs with database knowledge through automated exploration and instruction synthesis. DB-Explore c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04959","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/2503.04959/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":"2503.04959","created_at":"2026-07-05T11:06:29.223876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04959v2","created_at":"2026-07-05T11:06:29.223876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04959","created_at":"2026-07-05T11:06:29.223876+00:00"},{"alias_kind":"pith_short_12","alias_value":"G27DJKVDY3J4","created_at":"2026-07-05T11:06:29.223876+00:00"},{"alias_kind":"pith_short_16","alias_value":"G27DJKVDY3J42NCI","created_at":"2026-07-05T11:06:29.223876+00:00"},{"alias_kind":"pith_short_8","alias_value":"G27DJKVD","created_at":"2026-07-05T11:06:29.223876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28601","citing_title":"Database Context Compression for Text-to-SQL on Real-World Large Databases","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC","json":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC.json","graph_json":"https://pith.science/api/pith-number/G27DJKVDY3J42NCISGW74HKEQC/graph.json","events_json":"https://pith.science/api/pith-number/G27DJKVDY3J42NCISGW74HKEQC/events.json","paper":"https://pith.science/paper/G27DJKVD"},"agent_actions":{"view_html":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC","download_json":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC.json","view_paper":"https://pith.science/paper/G27DJKVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04959&json=true","fetch_graph":"https://pith.science/api/pith-number/G27DJKVDY3J42NCISGW74HKEQC/graph.json","fetch_events":"https://pith.science/api/pith-number/G27DJKVDY3J42NCISGW74HKEQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/action/storage_attestation","attest_author":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/action/author_attestation","sign_citation":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/action/citation_signature","submit_replication":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/action/replication_record"}},"created_at":"2026-07-05T11:06:29.223876+00:00","updated_at":"2026-07-05T11:06:29.223876+00:00"}