{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CDIGVUNQE35XYAY4C7VSLBN3BE","short_pith_number":"pith:CDIGVUNQ","schema_version":"1.0","canonical_sha256":"10d06ad1b026fb7c031c17eb2585bb093f90506c16e71b67886360985011f02a","source":{"kind":"arxiv","id":"2410.12916","version":2},"attestation_state":"computed","paper":{"title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangwei Yu, Ilan Gofman, Jesse C. Cresswell, Jiapeng Wu, No\\\"el Vouitsis, Rasa Hosseinzadeh, Satya Krishna Gorti, Zhaoyan Liu","submitted_at":"2024-10-16T18:03:24Z","abstract_excerpt":"Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other "},"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":"2410.12916","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T18:03:24Z","cross_cats_sorted":[],"title_canon_sha256":"c9fe8f6b9d931ce51408adf6f286be1ddec6b01f0b49a54601c9bf6259dcf17a","abstract_canon_sha256":"ef126e29a4ea608864744fdea2bb36b0f469f78e5dbe10cb6700cc170f4b389a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:46.856614Z","signature_b64":"8CbG/WUyrZysbAyH4OFXD5/T2ymwsgZZtDesaTAf4LIYWyAHK16HIlYgWX4sL2oQQe2853E1KdwJHML6J5IFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10d06ad1b026fb7c031c17eb2585bb093f90506c16e71b67886360985011f02a","last_reissued_at":"2026-07-05T10:14:46.856113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:46.856113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangwei Yu, Ilan Gofman, Jesse C. Cresswell, Jiapeng Wu, No\\\"el Vouitsis, Rasa Hosseinzadeh, Satya Krishna Gorti, Zhaoyan Liu","submitted_at":"2024-10-16T18:03:24Z","abstract_excerpt":"Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12916","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/2410.12916/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":"2410.12916","created_at":"2026-07-05T10:14:46.856168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12916v2","created_at":"2026-07-05T10:14:46.856168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12916","created_at":"2026-07-05T10:14:46.856168+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDIGVUNQE35X","created_at":"2026-07-05T10:14:46.856168+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDIGVUNQE35XYAY4","created_at":"2026-07-05T10:14:46.856168+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDIGVUNQ","created_at":"2026-07-05T10:14:46.856168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11986","citing_title":"Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE","json":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE.json","graph_json":"https://pith.science/api/pith-number/CDIGVUNQE35XYAY4C7VSLBN3BE/graph.json","events_json":"https://pith.science/api/pith-number/CDIGVUNQE35XYAY4C7VSLBN3BE/events.json","paper":"https://pith.science/paper/CDIGVUNQ"},"agent_actions":{"view_html":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE","download_json":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE.json","view_paper":"https://pith.science/paper/CDIGVUNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12916&json=true","fetch_graph":"https://pith.science/api/pith-number/CDIGVUNQE35XYAY4C7VSLBN3BE/graph.json","fetch_events":"https://pith.science/api/pith-number/CDIGVUNQE35XYAY4C7VSLBN3BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE/action/storage_attestation","attest_author":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE/action/author_attestation","sign_citation":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE/action/citation_signature","submit_replication":"https://pith.science/pith/CDIGVUNQE35XYAY4C7VSLBN3BE/action/replication_record"}},"created_at":"2026-07-05T10:14:46.856168+00:00","updated_at":"2026-07-05T10:14:46.856168+00:00"}