{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TIIHF7INFJZMPX5YV5HZHKFGHE","short_pith_number":"pith:TIIHF7IN","schema_version":"1.0","canonical_sha256":"9a1072fd0d2a72c7dfb8af4f93a8a63927fadc3756593da9ee082de28dab2074","source":{"kind":"arxiv","id":"2406.17761","version":3},"attestation_state":"computed","paper":{"title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Hung-Ting Chen, Ipsita Bhattacharjee, Marzena Karpinska, Mohit Iyyer, Shane Arora","submitted_at":"2024-06-25T17:45:26Z","abstract_excerpt":"Despite rising global usage of large language models (LLMs), their ability to generate long-form answers to culturally specific questions remains unexplored in many languages. To fill this gap, we perform the first study of textual multilingual long-form QA by creating CaLMQA, a dataset of 51.7K culturally specific questions across 23 different languages. We define culturally specific questions as those that refer to concepts unique to one or a few cultures, or have different answers depending on the cultural or regional context. We obtain these questions by crawling naturally-occurring questi"},"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":"2406.17761","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:45:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0d429c059ed76ccb2101c78d098c41449046bfde1838335b7c771e66148de0c5","abstract_canon_sha256":"3dd2dafcbc8f06164934d53ed2b84fbb74ce8f3221e052301ff5acd409d95e16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:48.958450Z","signature_b64":"4/iYGCdOFoaTwoxY2Vrz+rqnQp02ExBhO/bLWUpZMxqEc/FILsPgHovyBgMtpwA45ospajQmIl0HBqoTPTc2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a1072fd0d2a72c7dfb8af4f93a8a63927fadc3756593da9ee082de28dab2074","last_reissued_at":"2026-07-05T11:19:48.957952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:48.957952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Hung-Ting Chen, Ipsita Bhattacharjee, Marzena Karpinska, Mohit Iyyer, Shane Arora","submitted_at":"2024-06-25T17:45:26Z","abstract_excerpt":"Despite rising global usage of large language models (LLMs), their ability to generate long-form answers to culturally specific questions remains unexplored in many languages. To fill this gap, we perform the first study of textual multilingual long-form QA by creating CaLMQA, a dataset of 51.7K culturally specific questions across 23 different languages. We define culturally specific questions as those that refer to concepts unique to one or a few cultures, or have different answers depending on the cultural or regional context. We obtain these questions by crawling naturally-occurring questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17761","kind":"arxiv","version":3},"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/2406.17761/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":"2406.17761","created_at":"2026-07-05T11:19:48.958012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17761v3","created_at":"2026-07-05T11:19:48.958012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17761","created_at":"2026-07-05T11:19:48.958012+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIIHF7INFJZM","created_at":"2026-07-05T11:19:48.958012+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIIHF7INFJZMPX5Y","created_at":"2026-07-05T11:19:48.958012+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIIHF7IN","created_at":"2026-07-05T11:19:48.958012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17709","citing_title":"TyDi QA-WANA: A Benchmark for Information-Seeking Question Answering in Languages of West Asia and North Africa","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE","json":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE.json","graph_json":"https://pith.science/api/pith-number/TIIHF7INFJZMPX5YV5HZHKFGHE/graph.json","events_json":"https://pith.science/api/pith-number/TIIHF7INFJZMPX5YV5HZHKFGHE/events.json","paper":"https://pith.science/paper/TIIHF7IN"},"agent_actions":{"view_html":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE","download_json":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE.json","view_paper":"https://pith.science/paper/TIIHF7IN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17761&json=true","fetch_graph":"https://pith.science/api/pith-number/TIIHF7INFJZMPX5YV5HZHKFGHE/graph.json","fetch_events":"https://pith.science/api/pith-number/TIIHF7INFJZMPX5YV5HZHKFGHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE/action/storage_attestation","attest_author":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE/action/author_attestation","sign_citation":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE/action/citation_signature","submit_replication":"https://pith.science/pith/TIIHF7INFJZMPX5YV5HZHKFGHE/action/replication_record"}},"created_at":"2026-07-05T11:19:48.958012+00:00","updated_at":"2026-07-05T11:19:48.958012+00:00"}