{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RBPDDNXH7CQ7LJH5FVVY4RGF43","short_pith_number":"pith:RBPDDNXH","schema_version":"1.0","canonical_sha256":"885e31b6e7f8a1f5a4fd2d6b8e44c5e6d341e99ef405eed6496d9e6cca702161","source":{"kind":"arxiv","id":"2212.09278","version":1},"attestation_state":"computed","paper":{"title":"MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wenjie Ou, Yingwen Fu, Yue Lin, Zhou Yu","submitted_at":"2022-12-19T07:14:32Z","abstract_excerpt":"Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most state-of-the-art conversational text- to-SQL methods are incompatible with generative pre-trained language models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs' ability to tackle conversational text-to-SQL. In the pre-training stage, MIGA first decomposes the main task into several related sub-tasks and then unifies them into the same sequence-to-sequence (Seq2Seq) paradigm with task-s"},"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":"2212.09278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T07:14:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"105aeb40cd595cad8e02d4fac5568759bbe159d07385c5b7cc2e275aac77afea","abstract_canon_sha256":"07f7e3604c37fc4030a495d1bdfc15df184409c596105578aa42eb9e0920c792"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:20.479951Z","signature_b64":"xylcMTDuAsEukCBpPR6GB/HY75G4Iv8VCIEdH4PNarsxJOZRqMSybDOPxZZW5Nn6oJMV0WPAAPDWjMLCJD2WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"885e31b6e7f8a1f5a4fd2d6b8e44c5e6d341e99ef405eed6496d9e6cca702161","last_reissued_at":"2026-07-05T05:26:20.479447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:20.479447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wenjie Ou, Yingwen Fu, Yue Lin, Zhou Yu","submitted_at":"2022-12-19T07:14:32Z","abstract_excerpt":"Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most state-of-the-art conversational text- to-SQL methods are incompatible with generative pre-trained language models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs' ability to tackle conversational text-to-SQL. In the pre-training stage, MIGA first decomposes the main task into several related sub-tasks and then unifies them into the same sequence-to-sequence (Seq2Seq) paradigm with task-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09278","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/2212.09278/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":"2212.09278","created_at":"2026-07-05T05:26:20.479513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09278v1","created_at":"2026-07-05T05:26:20.479513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09278","created_at":"2026-07-05T05:26:20.479513+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBPDDNXH7CQ7","created_at":"2026-07-05T05:26:20.479513+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBPDDNXH7CQ7LJH5","created_at":"2026-07-05T05:26:20.479513+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBPDDNXH","created_at":"2026-07-05T05:26:20.479513+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/RBPDDNXH7CQ7LJH5FVVY4RGF43","json":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43.json","graph_json":"https://pith.science/api/pith-number/RBPDDNXH7CQ7LJH5FVVY4RGF43/graph.json","events_json":"https://pith.science/api/pith-number/RBPDDNXH7CQ7LJH5FVVY4RGF43/events.json","paper":"https://pith.science/paper/RBPDDNXH"},"agent_actions":{"view_html":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43","download_json":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43.json","view_paper":"https://pith.science/paper/RBPDDNXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09278&json=true","fetch_graph":"https://pith.science/api/pith-number/RBPDDNXH7CQ7LJH5FVVY4RGF43/graph.json","fetch_events":"https://pith.science/api/pith-number/RBPDDNXH7CQ7LJH5FVVY4RGF43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43/action/storage_attestation","attest_author":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43/action/author_attestation","sign_citation":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43/action/citation_signature","submit_replication":"https://pith.science/pith/RBPDDNXH7CQ7LJH5FVVY4RGF43/action/replication_record"}},"created_at":"2026-07-05T05:26:20.479513+00:00","updated_at":"2026-07-05T05:26:20.479513+00:00"}