{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IW3H3ZBX5BAOOCEQWZCTFI27S4","short_pith_number":"pith:IW3H3ZBX","schema_version":"1.0","canonical_sha256":"45b67de437e840e70890b64532a35f9726c33b59e474d77b1ee12c1dfd3b94a9","source":{"kind":"arxiv","id":"2505.12768","version":2},"attestation_state":"computed","paper":{"title":"ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiqin Yang, Pingfu Chao, Tianyu Yang, Wenhao Jiang, Wenxuan Xie, Xialie Zhuang, Yaxun Dai, Yiying Yang, Yuhang Zhao","submitted_at":"2025-05-19T06:46:47Z","abstract_excerpt":"In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc signal for correction or selection, failing to integrate it into the generation process. This limitation hinders their ability to address reasoning errors as they occur, ultimately reducing query accuracy and robustness. To address this issue, we propose ReEx-SQL (Reasoning with Execution-Aware Reinforcement Learning), a framework for Text-to-SQL that enables models to interact wi"},"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":"2505.12768","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T06:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"a954dd6a24422d47ef7c5f5bcfb1beffbc6fe27725994a233d074e6baa45cc83","abstract_canon_sha256":"0112b61237553160520900d09dbdd26cc674d9263bf156e21c29aa471727b46c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:45.643786Z","signature_b64":"Zb4LFO0YMGNoXJLdubVprQvOaFp5MIBvbV+f+8HbBlT0cCrhvs7ofN1JDPwSaeB6NOzl0RHZQNttpLu2zfb3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b67de437e840e70890b64532a35f9726c33b59e474d77b1ee12c1dfd3b94a9","last_reissued_at":"2026-07-05T11:05:45.643330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:45.643330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiqin Yang, Pingfu Chao, Tianyu Yang, Wenhao Jiang, Wenxuan Xie, Xialie Zhuang, Yaxun Dai, Yiying Yang, Yuhang Zhao","submitted_at":"2025-05-19T06:46:47Z","abstract_excerpt":"In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc signal for correction or selection, failing to integrate it into the generation process. This limitation hinders their ability to address reasoning errors as they occur, ultimately reducing query accuracy and robustness. To address this issue, we propose ReEx-SQL (Reasoning with Execution-Aware Reinforcement Learning), a framework for Text-to-SQL that enables models to interact wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12768","kind":"arxiv","version":2},"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/2505.12768/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":"2505.12768","created_at":"2026-07-05T11:05:45.643381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12768v2","created_at":"2026-07-05T11:05:45.643381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12768","created_at":"2026-07-05T11:05:45.643381+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW3H3ZBX5BAO","created_at":"2026-07-05T11:05:45.643381+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW3H3ZBX5BAOOCEQ","created_at":"2026-07-05T11:05:45.643381+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW3H3ZBX","created_at":"2026-07-05T11:05:45.643381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06825","citing_title":"Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":100,"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":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4","json":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4.json","graph_json":"https://pith.science/api/pith-number/IW3H3ZBX5BAOOCEQWZCTFI27S4/graph.json","events_json":"https://pith.science/api/pith-number/IW3H3ZBX5BAOOCEQWZCTFI27S4/events.json","paper":"https://pith.science/paper/IW3H3ZBX"},"agent_actions":{"view_html":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4","download_json":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4.json","view_paper":"https://pith.science/paper/IW3H3ZBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12768&json=true","fetch_graph":"https://pith.science/api/pith-number/IW3H3ZBX5BAOOCEQWZCTFI27S4/graph.json","fetch_events":"https://pith.science/api/pith-number/IW3H3ZBX5BAOOCEQWZCTFI27S4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4/action/storage_attestation","attest_author":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4/action/author_attestation","sign_citation":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4/action/citation_signature","submit_replication":"https://pith.science/pith/IW3H3ZBX5BAOOCEQWZCTFI27S4/action/replication_record"}},"created_at":"2026-07-05T11:05:45.643381+00:00","updated_at":"2026-07-05T11:05:45.643381+00:00"}