{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7LPFWBJBYYEMHAK5S2WSU2ULC7","short_pith_number":"pith:7LPFWBJB","schema_version":"1.0","canonical_sha256":"fade5b0521c608c3815d96ad2a6a8b17e84f3bb47842e702e3cd79734f615083","source":{"kind":"arxiv","id":"2411.08599","version":3},"attestation_state":"computed","paper":{"title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jinyang Gao, Liyu Mou, Shiqi Li, Wei Li, Xiaorong Shi, Xiaoxia Li, Yifu Liu, Yiming Wang, Yingqi Gao, Yin Zhu, Yu Li, Yuntao Hong, Zhiling Luo","submitted_at":"2024-11-13T13:30:21Z","abstract_excerpt":"To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of traini"},"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":"2411.08599","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-13T13:30:21Z","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"d29a6faa5181d42ef6d10168895282803629249208aeb692637ef3c52d659911","abstract_canon_sha256":"50d662e8347f411c906bfce0d797c49b08ce786b87af1a7fc87f4014d7501006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:02.209152Z","signature_b64":"2RswETnBrtv2Y9sCXELpE/FqI+YdHx72aVBHx12vyvD3U0XFwWIR4DrwQdxbfH8wta8Vwp572ZJgeZz8ji3vCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fade5b0521c608c3815d96ad2a6a8b17e84f3bb47842e702e3cd79734f615083","last_reissued_at":"2026-07-05T10:12:02.208636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:02.208636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jinyang Gao, Liyu Mou, Shiqi Li, Wei Li, Xiaorong Shi, Xiaoxia Li, Yifu Liu, Yiming Wang, Yingqi Gao, Yin Zhu, Yu Li, Yuntao Hong, Zhiling Luo","submitted_at":"2024-11-13T13:30:21Z","abstract_excerpt":"To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08599","kind":"arxiv","version":3},"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/2411.08599/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":"2411.08599","created_at":"2026-07-05T10:12:02.208703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08599v3","created_at":"2026-07-05T10:12:02.208703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08599","created_at":"2026-07-05T10:12:02.208703+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LPFWBJBYYEM","created_at":"2026-07-05T10:12:02.208703+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LPFWBJBYYEMHAK5","created_at":"2026-07-05T10:12:02.208703+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LPFWBJB","created_at":"2026-07-05T10:12:02.208703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14174","citing_title":"Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01008","citing_title":"MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13045","citing_title":"Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04719","citing_title":"Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16493","citing_title":"NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07041","citing_title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7","json":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7.json","graph_json":"https://pith.science/api/pith-number/7LPFWBJBYYEMHAK5S2WSU2ULC7/graph.json","events_json":"https://pith.science/api/pith-number/7LPFWBJBYYEMHAK5S2WSU2ULC7/events.json","paper":"https://pith.science/paper/7LPFWBJB"},"agent_actions":{"view_html":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7","download_json":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7.json","view_paper":"https://pith.science/paper/7LPFWBJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08599&json=true","fetch_graph":"https://pith.science/api/pith-number/7LPFWBJBYYEMHAK5S2WSU2ULC7/graph.json","fetch_events":"https://pith.science/api/pith-number/7LPFWBJBYYEMHAK5S2WSU2ULC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7/action/storage_attestation","attest_author":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7/action/author_attestation","sign_citation":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7/action/citation_signature","submit_replication":"https://pith.science/pith/7LPFWBJBYYEMHAK5S2WSU2ULC7/action/replication_record"}},"created_at":"2026-07-05T10:12:02.208703+00:00","updated_at":"2026-07-05T10:12:02.208703+00:00"}