{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T3D2FRVOKA7LDHD2BNGWTVGZPV","short_pith_number":"pith:T3D2FRVO","schema_version":"1.0","canonical_sha256":"9ec7a2c6ae503eb19c7a0b4d69d4d97d473efd81174ff61e66521ac2373298ca","source":{"kind":"arxiv","id":"2312.11242","version":6},"attestation_state":"computed","paper":{"title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Wang, Changyu Ren, Di Yin, Jian Yang, Jiaqi Bai, Linzheng Chai, Qian-Wen Zhang, Xing Sun, Xinnian Liang, Zhao Yan, Zhoujun Li","submitted_at":"2023-12-18T14:40:20Z","abstract_excerpt":"Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on \"huge\" databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To address these challenges, we introduce MAC-SQL, a novel LLM-based multi-agent collaborative framework. Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to ac"},"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":"2312.11242","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T14:40:20Z","cross_cats_sorted":[],"title_canon_sha256":"1af782690631470e3563da8ab038123baae8e353448c113de907ae432419f0e1","abstract_canon_sha256":"828a66f9473621d81427f57364b49732abb99be70da320f73548f0e6f1fcb556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:02.619980Z","signature_b64":"PmbAcwNywYH0Gifz1Pa0/zzlgo8oIGoP/5ZiT95bp1kK2I9EemzDic0wjnr7UvEQvwQ4qFvu75wnrxMcXTqMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ec7a2c6ae503eb19c7a0b4d69d4d97d473efd81174ff61e66521ac2373298ca","last_reissued_at":"2026-07-05T10:33:02.619209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:02.619209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Wang, Changyu Ren, Di Yin, Jian Yang, Jiaqi Bai, Linzheng Chai, Qian-Wen Zhang, Xing Sun, Xinnian Liang, Zhao Yan, Zhoujun Li","submitted_at":"2023-12-18T14:40:20Z","abstract_excerpt":"Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on \"huge\" databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To address these challenges, we introduce MAC-SQL, a novel LLM-based multi-agent collaborative framework. Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11242","kind":"arxiv","version":6},"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/2312.11242/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":"2312.11242","created_at":"2026-07-05T10:33:02.619298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11242v6","created_at":"2026-07-05T10:33:02.619298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11242","created_at":"2026-07-05T10:33:02.619298+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3D2FRVOKA7L","created_at":"2026-07-05T10:33:02.619298+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3D2FRVOKA7LDHD2","created_at":"2026-07-05T10:33:02.619298+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3D2FRVO","created_at":"2026-07-05T10:33:02.619298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28387","citing_title":"Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19010","citing_title":"AgentNLQ: A General-Purpose Agent for Natural Language to SQL","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03465","citing_title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28028","citing_title":"Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07041","citing_title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV","json":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV.json","graph_json":"https://pith.science/api/pith-number/T3D2FRVOKA7LDHD2BNGWTVGZPV/graph.json","events_json":"https://pith.science/api/pith-number/T3D2FRVOKA7LDHD2BNGWTVGZPV/events.json","paper":"https://pith.science/paper/T3D2FRVO"},"agent_actions":{"view_html":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV","download_json":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV.json","view_paper":"https://pith.science/paper/T3D2FRVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11242&json=true","fetch_graph":"https://pith.science/api/pith-number/T3D2FRVOKA7LDHD2BNGWTVGZPV/graph.json","fetch_events":"https://pith.science/api/pith-number/T3D2FRVOKA7LDHD2BNGWTVGZPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV/action/storage_attestation","attest_author":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV/action/author_attestation","sign_citation":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV/action/citation_signature","submit_replication":"https://pith.science/pith/T3D2FRVOKA7LDHD2BNGWTVGZPV/action/replication_record"}},"created_at":"2026-07-05T10:33:02.619298+00:00","updated_at":"2026-07-05T10:33:02.619298+00:00"}