{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZYROUEKZWRW3JREJAZA7MDXEZJ","short_pith_number":"pith:ZYROUEKZ","schema_version":"1.0","canonical_sha256":"ce22ea1159b46db4c4890641f60ee4ca42dd3942a62c46164ecf1acf20540e6f","source":{"kind":"arxiv","id":"2406.03170","version":2},"attestation_state":"computed","paper":{"title":"StatBot.Swiss: Bilingual Open Data Exploration in Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cyril Matthey-Doret, Ellery Smith, Farhad Nooralahzadeh, Kurt Stockinger, Rapha\\\"el de Fondville, Sabine Maennel, Yi Zhang","submitted_at":"2024-06-05T12:03:19Z","abstract_excerpt":"The potential for improvements brought by Large Language Models (LLMs) in Text-to-SQL systems is mostly assessed on monolingual English datasets. However, LLMs' performance for other languages remains vastly unexplored. In this work, we release the StatBot.Swiss dataset, the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. The StatBot.Swiss dataset contains 455 natural language/SQL-pairs over 35 big databases with varying level of complexity for both English and German.\n  We evaluate the performance of state-of-the-art LLMs such as GPT-3.5-Turbo an"},"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":"2406.03170","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T12:03:19Z","cross_cats_sorted":[],"title_canon_sha256":"661b4aafdac912db479dbdc5b0c4889267d514db29fe97e766d8c0c5dd96060c","abstract_canon_sha256":"864c2b4b34cd57412a2012f037787bc366a23674491651f21865ec8e86191a1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:11.988311Z","signature_b64":"7NaKokO2LL1cMU6MAP6N/arQiI9ePbfA75UnUDC/IKrSolZzZNOly64mBQvZi6h1GLl+00CTLEYW/htfjzvNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce22ea1159b46db4c4890641f60ee4ca42dd3942a62c46164ecf1acf20540e6f","last_reissued_at":"2026-07-05T08:28:11.987914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:11.987914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StatBot.Swiss: Bilingual Open Data Exploration in Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cyril Matthey-Doret, Ellery Smith, Farhad Nooralahzadeh, Kurt Stockinger, Rapha\\\"el de Fondville, Sabine Maennel, Yi Zhang","submitted_at":"2024-06-05T12:03:19Z","abstract_excerpt":"The potential for improvements brought by Large Language Models (LLMs) in Text-to-SQL systems is mostly assessed on monolingual English datasets. However, LLMs' performance for other languages remains vastly unexplored. In this work, we release the StatBot.Swiss dataset, the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. The StatBot.Swiss dataset contains 455 natural language/SQL-pairs over 35 big databases with varying level of complexity for both English and German.\n  We evaluate the performance of state-of-the-art LLMs such as GPT-3.5-Turbo an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03170","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/2406.03170/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":"2406.03170","created_at":"2026-07-05T08:28:11.987969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03170v2","created_at":"2026-07-05T08:28:11.987969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03170","created_at":"2026-07-05T08:28:11.987969+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYROUEKZWRW3","created_at":"2026-07-05T08:28:11.987969+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYROUEKZWRW3JREJ","created_at":"2026-07-05T08:28:11.987969+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYROUEKZ","created_at":"2026-07-05T08:28:11.987969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21445","citing_title":"Text2Cypher Across Languages: Evaluating and Finetuning LLMs","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ","json":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ.json","graph_json":"https://pith.science/api/pith-number/ZYROUEKZWRW3JREJAZA7MDXEZJ/graph.json","events_json":"https://pith.science/api/pith-number/ZYROUEKZWRW3JREJAZA7MDXEZJ/events.json","paper":"https://pith.science/paper/ZYROUEKZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ","download_json":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ.json","view_paper":"https://pith.science/paper/ZYROUEKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03170&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYROUEKZWRW3JREJAZA7MDXEZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYROUEKZWRW3JREJAZA7MDXEZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZYROUEKZWRW3JREJAZA7MDXEZJ/action/replication_record"}},"created_at":"2026-07-05T08:28:11.987969+00:00","updated_at":"2026-07-05T08:28:11.987969+00:00"}