{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YRNBJ22SV2Q7W5MMZG25OLS7WF","short_pith_number":"pith:YRNBJ22S","schema_version":"1.0","canonical_sha256":"c45a14eb52aea1fb758cc9b5d72e5fb168e41a3423a9e17e2240c46d28270b6a","source":{"kind":"arxiv","id":"2408.07930","version":4},"attestation_state":"computed","paper":{"title":"MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Gaochen Wu, Wenxuan Xie","submitted_at":"2024-08-15T04:57:55Z","abstract_excerpt":"Recent In-Context Learning based methods have achieved remarkable success in Text-to-SQL task. However, there is still a large gap between the performance of these models and human performance on datasets with complex database schema and difficult questions, such as BIRD. Besides, existing work has neglected to supervise intermediate steps when solving questions iteratively with question decomposition methods, and the schema linking methods used in these works are very rudimentary. To address these issues, we propose MAG-SQL, a multi-agent generative approach with soft schema linking and itera"},"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":"2408.07930","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T04:57:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9e416f6dfc213c9a89469d69f4cde4a7c6f9d3e40d0062236b6b8b3e8671ff7","abstract_canon_sha256":"283f50f786d98926e0409351357a2b53a92d1f002a1efa216d90c0a0821a22f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:11.401445Z","signature_b64":"lmqEZemTfgjlxSvTt+mTI8wRtE/wqMCVh5hBfQ7mVABd9Nk55tmdd+LbMGmAZoefHCuaYpj8c0rNJPeXK3Z2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c45a14eb52aea1fb758cc9b5d72e5fb168e41a3423a9e17e2240c46d28270b6a","last_reissued_at":"2026-07-05T09:32:11.401021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:11.401021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Gaochen Wu, Wenxuan Xie","submitted_at":"2024-08-15T04:57:55Z","abstract_excerpt":"Recent In-Context Learning based methods have achieved remarkable success in Text-to-SQL task. However, there is still a large gap between the performance of these models and human performance on datasets with complex database schema and difficult questions, such as BIRD. Besides, existing work has neglected to supervise intermediate steps when solving questions iteratively with question decomposition methods, and the schema linking methods used in these works are very rudimentary. To address these issues, we propose MAG-SQL, a multi-agent generative approach with soft schema linking and itera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07930","kind":"arxiv","version":4},"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/2408.07930/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":"2408.07930","created_at":"2026-07-05T09:32:11.401078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07930v4","created_at":"2026-07-05T09:32:11.401078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07930","created_at":"2026-07-05T09:32:11.401078+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRNBJ22SV2Q7","created_at":"2026-07-05T09:32:11.401078+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRNBJ22SV2Q7W5MM","created_at":"2026-07-05T09:32:11.401078+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRNBJ22S","created_at":"2026-07-05T09:32:11.401078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.21480","citing_title":"Both Ends Count! Just How Good are LLM Agents at \"Text-to-Big SQL\"?","ref_index":54,"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":193,"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":208,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF","json":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF.json","graph_json":"https://pith.science/api/pith-number/YRNBJ22SV2Q7W5MMZG25OLS7WF/graph.json","events_json":"https://pith.science/api/pith-number/YRNBJ22SV2Q7W5MMZG25OLS7WF/events.json","paper":"https://pith.science/paper/YRNBJ22S"},"agent_actions":{"view_html":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF","download_json":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF.json","view_paper":"https://pith.science/paper/YRNBJ22S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07930&json=true","fetch_graph":"https://pith.science/api/pith-number/YRNBJ22SV2Q7W5MMZG25OLS7WF/graph.json","fetch_events":"https://pith.science/api/pith-number/YRNBJ22SV2Q7W5MMZG25OLS7WF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF/action/storage_attestation","attest_author":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF/action/author_attestation","sign_citation":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF/action/citation_signature","submit_replication":"https://pith.science/pith/YRNBJ22SV2Q7W5MMZG25OLS7WF/action/replication_record"}},"created_at":"2026-07-05T09:32:11.401078+00:00","updated_at":"2026-07-05T09:32:11.401078+00:00"}