{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KXLPV2U6PILG4FF5EPEP7EWCSR","short_pith_number":"pith:KXLPV2U6","schema_version":"1.0","canonical_sha256":"55d6faea9e7a166e14bd23c8ff92c29448ba70033540989cd9f327bb9a963094","source":{"kind":"arxiv","id":"2505.18929","version":1},"attestation_state":"computed","paper":{"title":"Meta-aware Learning in text-to-SQL Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Wenda Zhang","submitted_at":"2025-05-25T01:45:00Z","abstract_excerpt":"The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In this paper, we propose a meta-aware learning framework to integrate domain knowledge, database schema, chain-of-thought reasoning processes, and metadata relationships to improve the SQL generation quality. The proposed framework includes four learning strategies: schema-based learning, Chain-of-Thought (CoT) learning, knowledge-enhanced learning, and key info"},"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":"2505.18929","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-25T01:45:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"83d290406609d133f5e3c1402d89b544f25839f42b79fee87facc8e4c4b52531","abstract_canon_sha256":"5b0b73ef18a6b8824986d87dc864239c48ab69b2c65ee963f9265bad0f87cd31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:21.973474Z","signature_b64":"3RcWzh5VeZjDO+LG31AVNH4Zeobtr1e6ILvxlwx23Pjsq1fj2NonLmnZo41cU4ZjY3V4W5uR784ejKIwnoNiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d6faea9e7a166e14bd23c8ff92c29448ba70033540989cd9f327bb9a963094","last_reissued_at":"2026-07-05T11:09:21.972971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:21.972971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-aware Learning in text-to-SQL Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Wenda Zhang","submitted_at":"2025-05-25T01:45:00Z","abstract_excerpt":"The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In this paper, we propose a meta-aware learning framework to integrate domain knowledge, database schema, chain-of-thought reasoning processes, and metadata relationships to improve the SQL generation quality. The proposed framework includes four learning strategies: schema-based learning, Chain-of-Thought (CoT) learning, knowledge-enhanced learning, and key info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18929","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/2505.18929/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":"2505.18929","created_at":"2026-07-05T11:09:21.973029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18929v1","created_at":"2026-07-05T11:09:21.973029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18929","created_at":"2026-07-05T11:09:21.973029+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXLPV2U6PILG","created_at":"2026-07-05T11:09:21.973029+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXLPV2U6PILG4FF5","created_at":"2026-07-05T11:09:21.973029+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXLPV2U6","created_at":"2026-07-05T11:09:21.973029+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/KXLPV2U6PILG4FF5EPEP7EWCSR","json":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR.json","graph_json":"https://pith.science/api/pith-number/KXLPV2U6PILG4FF5EPEP7EWCSR/graph.json","events_json":"https://pith.science/api/pith-number/KXLPV2U6PILG4FF5EPEP7EWCSR/events.json","paper":"https://pith.science/paper/KXLPV2U6"},"agent_actions":{"view_html":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR","download_json":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR.json","view_paper":"https://pith.science/paper/KXLPV2U6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18929&json=true","fetch_graph":"https://pith.science/api/pith-number/KXLPV2U6PILG4FF5EPEP7EWCSR/graph.json","fetch_events":"https://pith.science/api/pith-number/KXLPV2U6PILG4FF5EPEP7EWCSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR/action/storage_attestation","attest_author":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR/action/author_attestation","sign_citation":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR/action/citation_signature","submit_replication":"https://pith.science/pith/KXLPV2U6PILG4FF5EPEP7EWCSR/action/replication_record"}},"created_at":"2026-07-05T11:09:21.973029+00:00","updated_at":"2026-07-05T11:09:21.973029+00:00"}