{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AMIBFXEEZCSWTEFQYQDK562ACM","short_pith_number":"pith:AMIBFXEE","schema_version":"1.0","canonical_sha256":"031012dc84c8a56990b0c406aefb4013130068ca7c86132b3cff22f73a97f0e8","source":{"kind":"arxiv","id":"2212.13492","version":1},"attestation_state":"computed","paper":{"title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dechen Zhan, Dingzirui Wang, Jian-Guang Lou, Longxu Dou, Mingyang Pan, Wanxiang Che, Yan Gao","submitted_at":"2022-12-27T13:58:30Z","abstract_excerpt":"Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems. Much recent progress in text-to-SQL has been driven by large-scale datasets, but most of them are centered on English. In this work, we present MultiSpider, the largest multilingual text-to-SQL dataset which covers seven languages (English, German, French, Spanish, Japanese, Chinese, and Vietnamese). Upon MultiSpider, we further identify the lexical and structural challenges of text-to-SQL (caus"},"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":"2212.13492","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-27T13:58:30Z","cross_cats_sorted":[],"title_canon_sha256":"61fa3077f8a60fb635c5116a914ebcd5daf544681a3cca2be713d7dde78439d0","abstract_canon_sha256":"fdd5b3502325918332ee7f05d9cce5b477be1fd101b3a400947ba36515885096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:52.209078Z","signature_b64":"LqLK0ND/VQcSGATWRk2vxsB/OdktETw+Mdqqojs0+RJ48tghmyleP3PhKgTjzLRwXDyNq2hs9gXPcAG42EASCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"031012dc84c8a56990b0c406aefb4013130068ca7c86132b3cff22f73a97f0e8","last_reissued_at":"2026-07-05T05:28:52.208564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:52.208564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dechen Zhan, Dingzirui Wang, Jian-Guang Lou, Longxu Dou, Mingyang Pan, Wanxiang Che, Yan Gao","submitted_at":"2022-12-27T13:58:30Z","abstract_excerpt":"Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems. Much recent progress in text-to-SQL has been driven by large-scale datasets, but most of them are centered on English. In this work, we present MultiSpider, the largest multilingual text-to-SQL dataset which covers seven languages (English, German, French, Spanish, Japanese, Chinese, and Vietnamese). Upon MultiSpider, we further identify the lexical and structural challenges of text-to-SQL (caus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13492","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/2212.13492/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":"2212.13492","created_at":"2026-07-05T05:28:52.208617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13492v1","created_at":"2026-07-05T05:28:52.208617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13492","created_at":"2026-07-05T05:28:52.208617+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMIBFXEEZCSW","created_at":"2026-07-05T05:28:52.208617+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMIBFXEEZCSWTEFQ","created_at":"2026-07-05T05:28:52.208617+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMIBFXEE","created_at":"2026-07-05T05:28:52.208617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18254","citing_title":"LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM","json":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM.json","graph_json":"https://pith.science/api/pith-number/AMIBFXEEZCSWTEFQYQDK562ACM/graph.json","events_json":"https://pith.science/api/pith-number/AMIBFXEEZCSWTEFQYQDK562ACM/events.json","paper":"https://pith.science/paper/AMIBFXEE"},"agent_actions":{"view_html":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM","download_json":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM.json","view_paper":"https://pith.science/paper/AMIBFXEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13492&json=true","fetch_graph":"https://pith.science/api/pith-number/AMIBFXEEZCSWTEFQYQDK562ACM/graph.json","fetch_events":"https://pith.science/api/pith-number/AMIBFXEEZCSWTEFQYQDK562ACM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM/action/storage_attestation","attest_author":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM/action/author_attestation","sign_citation":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM/action/citation_signature","submit_replication":"https://pith.science/pith/AMIBFXEEZCSWTEFQYQDK562ACM/action/replication_record"}},"created_at":"2026-07-05T05:28:52.208617+00:00","updated_at":"2026-07-05T05:28:52.208617+00:00"}