{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FBVEL5VD3FRZR2PGG6FWEH7ICI","short_pith_number":"pith:FBVEL5VD","schema_version":"1.0","canonical_sha256":"286a45f6a3d96398e9e6378b621fe8123de5a11bd4383d4888473235f754dfe9","source":{"kind":"arxiv","id":"2607.22622","version":1},"attestation_state":"computed","paper":{"title":"Learning When to Reason for Text-to-SQL via SFT and DPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiheum Yeom, Kiwook Bae, Nohil Park, Sang Hun Kim, Soohyuk Jang, Sungroh Yoon, Yoonyoung Choi","submitted_at":"2026-06-17T06:31:28Z","abstract_excerpt":"Recent Text-to-SQL methods rely heavily on reasoning-centric paradigms such as Chain-of-Thought (CoT), achieving substantial gains on complex benchmarks at the cost of high inference-time overhead. However, a large fraction of real-world queries are simple lookups or aggregations that can be resolved without multi-step deduction, making forced reasoning wasteful. Thus, we propose AutoThinkSQL, a framework that integrates an auto-thinking mechanism into both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) on Text-to-SQL. Our approach enables the model to dynamically bypass"},"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":"2607.22622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T06:31:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"842a9d35ce23c59fecbe723c08d20f16484efe31acc44f316de13e35f5491822","abstract_canon_sha256":"d41f63752f53a1ea28176a28ece466026cd905027c6ca94e35a69ac7ea00b508"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:45.616174Z","signature_b64":"NKicheET9e+JwqEapK/LTRfSJKLgXXUBRx3PQINw89D8AqXxgdQ/upsG1fixB9UGz8ULLJu6MSzybXqKCdCuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"286a45f6a3d96398e9e6378b621fe8123de5a11bd4383d4888473235f754dfe9","last_reissued_at":"2026-07-28T00:21:45.615292Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:45.615292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning When to Reason for Text-to-SQL via SFT and DPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiheum Yeom, Kiwook Bae, Nohil Park, Sang Hun Kim, Soohyuk Jang, Sungroh Yoon, Yoonyoung Choi","submitted_at":"2026-06-17T06:31:28Z","abstract_excerpt":"Recent Text-to-SQL methods rely heavily on reasoning-centric paradigms such as Chain-of-Thought (CoT), achieving substantial gains on complex benchmarks at the cost of high inference-time overhead. However, a large fraction of real-world queries are simple lookups or aggregations that can be resolved without multi-step deduction, making forced reasoning wasteful. Thus, we propose AutoThinkSQL, a framework that integrates an auto-thinking mechanism into both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) on Text-to-SQL. Our approach enables the model to dynamically bypass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22622","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/2607.22622/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":"2607.22622","created_at":"2026-07-28T00:21:45.615754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22622v1","created_at":"2026-07-28T00:21:45.615754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22622","created_at":"2026-07-28T00:21:45.615754+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBVEL5VD3FRZ","created_at":"2026-07-28T00:21:45.615754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBVEL5VD3FRZR2PG","created_at":"2026-07-28T00:21:45.615754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBVEL5VD","created_at":"2026-07-28T00:21:45.615754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI","json":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI.json","graph_json":"https://pith.science/api/pith-number/FBVEL5VD3FRZR2PGG6FWEH7ICI/graph.json","events_json":"https://pith.science/api/pith-number/FBVEL5VD3FRZR2PGG6FWEH7ICI/events.json","paper":"https://pith.science/paper/FBVEL5VD"},"agent_actions":{"view_html":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI","download_json":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI.json","view_paper":"https://pith.science/paper/FBVEL5VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22622&json=true","fetch_graph":"https://pith.science/api/pith-number/FBVEL5VD3FRZR2PGG6FWEH7ICI/graph.json","fetch_events":"https://pith.science/api/pith-number/FBVEL5VD3FRZR2PGG6FWEH7ICI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI/action/storage_attestation","attest_author":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI/action/author_attestation","sign_citation":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI/action/citation_signature","submit_replication":"https://pith.science/pith/FBVEL5VD3FRZR2PGG6FWEH7ICI/action/replication_record"}},"created_at":"2026-07-28T00:21:45.615754+00:00","updated_at":"2026-07-28T00:21:45.615754+00:00"}