{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6USXZ6DV5R7CHO3RGT5B7DWD3S","short_pith_number":"pith:6USXZ6DV","schema_version":"1.0","canonical_sha256":"f5257cf875ec7e23bb7134fa1f8ec3dca922f9e1d739e40dca2509973924b26a","source":{"kind":"arxiv","id":"2502.06759","version":4},"attestation_state":"computed","paper":{"title":"Rationalization Models for Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Dharmashankar Subramanian, Gaetano Rossiello, Junkyu Lee, Michael Glass, Nhan Pham","submitted_at":"2025-02-10T18:38:57Z","abstract_excerpt":"We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and explanations, serving as incremental steps toward constructing the final SQL query. The process begins with manually annotating a small set of examples, which are then used to prompt a large language model in an iterative, dynamic few-shot knowledge distillation procedure from a teacher model. A rationalization model is subsequently trained on the validated decomposed queries, enabling extensive synthetic CoT annotations"},"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":"2502.06759","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T18:38:57Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"0a448b3f87f4366b44aa68fa360710e51d6c2b0b8b751d974188dba06af953ce","abstract_canon_sha256":"b8c341597d80c95624e439a0fd0e1a6adbf9e9678a20939d24b7acdef2a9f497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:45.984555Z","signature_b64":"1e2jbIycJttLs4KGZSzu0Lkv1S0gOKWtgKxHJy39JiqCNLKAhqpyfp9N3x7FqNBtGH4GJ2FC+Z7J1qAWIG3tBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5257cf875ec7e23bb7134fa1f8ec3dca922f9e1d739e40dca2509973924b26a","last_reissued_at":"2026-07-05T10:35:45.984055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:45.984055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rationalization Models for Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Dharmashankar Subramanian, Gaetano Rossiello, Junkyu Lee, Michael Glass, Nhan Pham","submitted_at":"2025-02-10T18:38:57Z","abstract_excerpt":"We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and explanations, serving as incremental steps toward constructing the final SQL query. The process begins with manually annotating a small set of examples, which are then used to prompt a large language model in an iterative, dynamic few-shot knowledge distillation procedure from a teacher model. A rationalization model is subsequently trained on the validated decomposed queries, enabling extensive synthetic CoT annotations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06759","kind":"arxiv","version":4},"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/2502.06759/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":"2502.06759","created_at":"2026-07-05T10:35:45.984113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06759v4","created_at":"2026-07-05T10:35:45.984113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06759","created_at":"2026-07-05T10:35:45.984113+00:00"},{"alias_kind":"pith_short_12","alias_value":"6USXZ6DV5R7C","created_at":"2026-07-05T10:35:45.984113+00:00"},{"alias_kind":"pith_short_16","alias_value":"6USXZ6DV5R7CHO3R","created_at":"2026-07-05T10:35:45.984113+00:00"},{"alias_kind":"pith_short_8","alias_value":"6USXZ6DV","created_at":"2026-07-05T10:35:45.984113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":258,"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":273,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S","json":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S.json","graph_json":"https://pith.science/api/pith-number/6USXZ6DV5R7CHO3RGT5B7DWD3S/graph.json","events_json":"https://pith.science/api/pith-number/6USXZ6DV5R7CHO3RGT5B7DWD3S/events.json","paper":"https://pith.science/paper/6USXZ6DV"},"agent_actions":{"view_html":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S","download_json":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S.json","view_paper":"https://pith.science/paper/6USXZ6DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06759&json=true","fetch_graph":"https://pith.science/api/pith-number/6USXZ6DV5R7CHO3RGT5B7DWD3S/graph.json","fetch_events":"https://pith.science/api/pith-number/6USXZ6DV5R7CHO3RGT5B7DWD3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S/action/storage_attestation","attest_author":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S/action/author_attestation","sign_citation":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S/action/citation_signature","submit_replication":"https://pith.science/pith/6USXZ6DV5R7CHO3RGT5B7DWD3S/action/replication_record"}},"created_at":"2026-07-05T10:35:45.984113+00:00","updated_at":"2026-07-05T10:35:45.984113+00:00"}