{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZJGPBBWHBCPN2C7DQALTUMPVS","short_pith_number":"pith:KZJGPBBW","schema_version":"1.0","canonical_sha256":"56526784363844f6e85f1c00b9d18fac874fe1107c612e2b778cc52f7d7a0aa5","source":{"kind":"arxiv","id":"2502.13550","version":1},"attestation_state":"computed","paper":{"title":"STaR-SQL: Self-Taught Reasoner for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Wang, Mingqian He, Qiuying Peng, Weiming Lu, Wenqi Zhang, Yongliang Shen","submitted_at":"2025-02-19T08:58:44Z","abstract_excerpt":"Generating step-by-step \"chain-of-thought\" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such techniques to structured tasks, such as text-to-SQL, remains largely unexplored. In this paper, we introduce Self-Taught Reasoner for text-to-SQL (STaR-SQL), a novel approach that reframes SQL query generation as a reasoning-driven process. Our method prompts the LLM to produce detailed reasoning steps for SQL queries and fine-tunes it on rationales that lead to correct outcomes. Unlike traditional methods, STaR-SQL"},"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":"2502.13550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T08:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"99116f4710bda4a608996895f6f515d8d3dc007013aab6dc42edb79e20c7c10b","abstract_canon_sha256":"89b7cd845af68535f3e9c69fe3cd95e3fc758fca1f2c014acb185de4fcca4724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:49.064409Z","signature_b64":"zTx7X8ts8gfOhNvgljNNYmUnlTkJaSzYjGENtxJpIjoKC7iPfaTCUWTSKQBW/jnSiskVl8UAc7+cZMxw0ouVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56526784363844f6e85f1c00b9d18fac874fe1107c612e2b778cc52f7d7a0aa5","last_reissued_at":"2026-07-05T10:16:49.063922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:49.063922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STaR-SQL: Self-Taught Reasoner for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Wang, Mingqian He, Qiuying Peng, Weiming Lu, Wenqi Zhang, Yongliang Shen","submitted_at":"2025-02-19T08:58:44Z","abstract_excerpt":"Generating step-by-step \"chain-of-thought\" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such techniques to structured tasks, such as text-to-SQL, remains largely unexplored. In this paper, we introduce Self-Taught Reasoner for text-to-SQL (STaR-SQL), a novel approach that reframes SQL query generation as a reasoning-driven process. Our method prompts the LLM to produce detailed reasoning steps for SQL queries and fine-tunes it on rationales that lead to correct outcomes. Unlike traditional methods, STaR-SQL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13550","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/2502.13550/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":"2502.13550","created_at":"2026-07-05T10:16:49.063981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13550v1","created_at":"2026-07-05T10:16:49.063981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13550","created_at":"2026-07-05T10:16:49.063981+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZJGPBBWHBCP","created_at":"2026-07-05T10:16:49.063981+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZJGPBBWHBCPN2C7","created_at":"2026-07-05T10:16:49.063981+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZJGPBBW","created_at":"2026-07-05T10:16:49.063981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20055","citing_title":"VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01474","citing_title":"ReMedi: Reasoner for Medical Clinical Prediction","ref_index":32,"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":257,"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":272,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS","json":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS.json","graph_json":"https://pith.science/api/pith-number/KZJGPBBWHBCPN2C7DQALTUMPVS/graph.json","events_json":"https://pith.science/api/pith-number/KZJGPBBWHBCPN2C7DQALTUMPVS/events.json","paper":"https://pith.science/paper/KZJGPBBW"},"agent_actions":{"view_html":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS","download_json":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS.json","view_paper":"https://pith.science/paper/KZJGPBBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13550&json=true","fetch_graph":"https://pith.science/api/pith-number/KZJGPBBWHBCPN2C7DQALTUMPVS/graph.json","fetch_events":"https://pith.science/api/pith-number/KZJGPBBWHBCPN2C7DQALTUMPVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS/action/storage_attestation","attest_author":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS/action/author_attestation","sign_citation":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS/action/citation_signature","submit_replication":"https://pith.science/pith/KZJGPBBWHBCPN2C7DQALTUMPVS/action/replication_record"}},"created_at":"2026-07-05T10:16:49.063981+00:00","updated_at":"2026-07-05T10:16:49.063981+00:00"}