{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ETYAOLTQVM2HETLGXLSAYI4D3O","short_pith_number":"pith:ETYAOLTQ","schema_version":"1.0","canonical_sha256":"24f0072e70ab34724d66bae40c2383dbb6b38a828a2e72e3c51aec77146880d3","source":{"kind":"arxiv","id":"2605.21792","version":1},"attestation_state":"computed","paper":{"title":"Residual Skill Optimization for Text-to-SQL Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Babak Salimi, Canwen Xu, Haoquan Guan, Jiongli Zhu, Nikki Lijing Kuang, Parjanya Prajakta Prashant, Seyedeh Baharan Khatami, Xiaodong Yu, Yingyu Lin, Yuxiong He, Zhewei Yao","submitted_at":"2026-05-20T22:36:11Z","abstract_excerpt":"Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails o"},"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":"2605.21792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T22:36:11Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"title_canon_sha256":"b77e0923a742aa626c8815983f24c17efa887f165560d39ec188e11a13e4da78","abstract_canon_sha256":"decb0cf464e14bab96198d96b6724739713df7800ad5182172501006ac108a1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:32.666599Z","signature_b64":"3zQNehkk59gBFMIHK1NtZhj1AE2AhSAPQhB12ErQK0e9oXNA88M7s+bohmd4V4G2E5ghDs8m3rZABnE8TnIuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24f0072e70ab34724d66bae40c2383dbb6b38a828a2e72e3c51aec77146880d3","last_reissued_at":"2026-05-22T01:03:32.666122Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:32.666122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Skill Optimization for Text-to-SQL Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Babak Salimi, Canwen Xu, Haoquan Guan, Jiongli Zhu, Nikki Lijing Kuang, Parjanya Prajakta Prashant, Seyedeh Baharan Khatami, Xiaodong Yu, Yingyu Lin, Yuxiong He, Zhewei Yao","submitted_at":"2026-05-20T22:36:11Z","abstract_excerpt":"Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21792","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/2605.21792/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":"2605.21792","created_at":"2026-05-22T01:03:32.666193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21792v1","created_at":"2026-05-22T01:03:32.666193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21792","created_at":"2026-05-22T01:03:32.666193+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETYAOLTQVM2H","created_at":"2026-05-22T01:03:32.666193+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETYAOLTQVM2HETLG","created_at":"2026-05-22T01:03:32.666193+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETYAOLTQ","created_at":"2026-05-22T01:03:32.666193+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/ETYAOLTQVM2HETLGXLSAYI4D3O","json":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O.json","graph_json":"https://pith.science/api/pith-number/ETYAOLTQVM2HETLGXLSAYI4D3O/graph.json","events_json":"https://pith.science/api/pith-number/ETYAOLTQVM2HETLGXLSAYI4D3O/events.json","paper":"https://pith.science/paper/ETYAOLTQ"},"agent_actions":{"view_html":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O","download_json":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O.json","view_paper":"https://pith.science/paper/ETYAOLTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21792&json=true","fetch_graph":"https://pith.science/api/pith-number/ETYAOLTQVM2HETLGXLSAYI4D3O/graph.json","fetch_events":"https://pith.science/api/pith-number/ETYAOLTQVM2HETLGXLSAYI4D3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O/action/storage_attestation","attest_author":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O/action/author_attestation","sign_citation":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O/action/citation_signature","submit_replication":"https://pith.science/pith/ETYAOLTQVM2HETLGXLSAYI4D3O/action/replication_record"}},"created_at":"2026-05-22T01:03:32.666193+00:00","updated_at":"2026-05-22T01:03:32.666193+00:00"}