{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RKSZP2465WFNOKI326YYQ7NZIG","short_pith_number":"pith:RKSZP246","schema_version":"1.0","canonical_sha256":"8aa597eb9eed8ad7291bd7b1887db941bc723f50ad6745736c06e3f6b03fd962","source":{"kind":"arxiv","id":"2509.07159","version":1},"attestation_state":"computed","paper":{"title":"PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baruch Gutow, Davoud Ataee Tarzanagh, Hankyu Moon, Heng Hao, Masoud Faraki, Oxana Verkholyak, Seungjai Min, Sima Didari, Wenjun Hu","submitted_at":"2025-09-08T19:15:38Z","abstract_excerpt":"Text-to-SQL models allow users to interact with a database more easily by generating executable SQL statements from natural-language questions. Despite recent successes on simpler databases and questions, current Text-to-SQL methods still suffer from low execution accuracy on industry-scale databases and complex questions involving domain-specific business logic. We present \\emph{PaVeRL-SQL}, a framework that combines \\emph{Partial-Match Rewards} and \\emph{Verbal Reinforcement Learning} to drive self-improvement in reasoning language models (RLMs) for Text-to-SQL. To handle practical use cases"},"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":"2509.07159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-08T19:15:38Z","cross_cats_sorted":[],"title_canon_sha256":"2d41a9dc511299acbdf46ffb7810b88046d1db8a203c9a1271dd1c9215afbfd8","abstract_canon_sha256":"9627ec7b09fb5944bf4a9a9f119a53c5b05acccb56907cf2bfd67ff5df4e2aad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:16.648440Z","signature_b64":"PkgLmgQwl2zEImoCMa83D0rB8F5GVD1rUDEI8a8eN+TOtVpivco/kxohG73Uq/uhm8A6Yx0eBteNaR7f+/7GBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa597eb9eed8ad7291bd7b1887db941bc723f50ad6745736c06e3f6b03fd962","last_reissued_at":"2026-07-05T12:07:16.647862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:16.647862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baruch Gutow, Davoud Ataee Tarzanagh, Hankyu Moon, Heng Hao, Masoud Faraki, Oxana Verkholyak, Seungjai Min, Sima Didari, Wenjun Hu","submitted_at":"2025-09-08T19:15:38Z","abstract_excerpt":"Text-to-SQL models allow users to interact with a database more easily by generating executable SQL statements from natural-language questions. Despite recent successes on simpler databases and questions, current Text-to-SQL methods still suffer from low execution accuracy on industry-scale databases and complex questions involving domain-specific business logic. We present \\emph{PaVeRL-SQL}, a framework that combines \\emph{Partial-Match Rewards} and \\emph{Verbal Reinforcement Learning} to drive self-improvement in reasoning language models (RLMs) for Text-to-SQL. To handle practical use cases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07159","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/2509.07159/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":"2509.07159","created_at":"2026-07-05T12:07:16.647927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07159v1","created_at":"2026-07-05T12:07:16.647927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07159","created_at":"2026-07-05T12:07:16.647927+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKSZP2465WFN","created_at":"2026-07-05T12:07:16.647927+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKSZP2465WFNOKI3","created_at":"2026-07-05T12:07:16.647927+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKSZP246","created_at":"2026-07-05T12:07:16.647927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG","json":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG.json","graph_json":"https://pith.science/api/pith-number/RKSZP2465WFNOKI326YYQ7NZIG/graph.json","events_json":"https://pith.science/api/pith-number/RKSZP2465WFNOKI326YYQ7NZIG/events.json","paper":"https://pith.science/paper/RKSZP246"},"agent_actions":{"view_html":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG","download_json":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG.json","view_paper":"https://pith.science/paper/RKSZP246","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07159&json=true","fetch_graph":"https://pith.science/api/pith-number/RKSZP2465WFNOKI326YYQ7NZIG/graph.json","fetch_events":"https://pith.science/api/pith-number/RKSZP2465WFNOKI326YYQ7NZIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG/action/storage_attestation","attest_author":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG/action/author_attestation","sign_citation":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG/action/citation_signature","submit_replication":"https://pith.science/pith/RKSZP2465WFNOKI326YYQ7NZIG/action/replication_record"}},"created_at":"2026-07-05T12:07:16.647927+00:00","updated_at":"2026-07-05T12:07:16.647927+00:00"}