{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ODEO6OSGQF2RL2BO5YBRA2W3QM","short_pith_number":"pith:ODEO6OSG","schema_version":"1.0","canonical_sha256":"70c8ef3a46817515e82eee03106adb830da9c98895bef480e767715283cfe0e5","source":{"kind":"arxiv","id":"2408.10604","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Non-Factoid Question Answering with Answer Paragraph Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ponnurangam Kumaraguru, Rajiv Ratn Shah, Ritwik Mishra, Sreeram Vennam","submitted_at":"2024-08-20T07:37:06Z","abstract_excerpt":"Most existing Question Answering Datasets (QuADs) primarily focus on factoid-based short-context Question Answering (QA) in high-resource languages. However, the scope of such datasets for low-resource languages remains limited, with only a few works centered on factoid-based QuADs and none on non-factoid QuADs. Therefore, this work presents MuNfQuAD, a multilingual QuAD with non-factoid questions. It utilizes interrogative sub-headings from BBC news articles as questions and the corresponding paragraphs as silver answers. The dataset comprises over 578K QA pairs across 38 languages, encompass"},"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":"2408.10604","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T07:37:06Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"2ecfd1a43d4d5659c25247fdb0368a2a9f9b469d0c40e05d7d7b8d7de606aa4c","abstract_canon_sha256":"1d2a047307730d2cf9a8a9c16b17a068a6b5cf60427b65ba5c4b2e8ccef73a5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:58.850253Z","signature_b64":"JWrTZroxS+BBp+nB4PVn8n3kVBAFNFLvIuop1a2TLyx4z5oDHvfQU/7ym76WJ+xuKQWyUEFt+991wRwPNPD/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c8ef3a46817515e82eee03106adb830da9c98895bef480e767715283cfe0e5","last_reissued_at":"2026-07-05T10:16:58.849839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:58.849839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Non-Factoid Question Answering with Answer Paragraph Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ponnurangam Kumaraguru, Rajiv Ratn Shah, Ritwik Mishra, Sreeram Vennam","submitted_at":"2024-08-20T07:37:06Z","abstract_excerpt":"Most existing Question Answering Datasets (QuADs) primarily focus on factoid-based short-context Question Answering (QA) in high-resource languages. However, the scope of such datasets for low-resource languages remains limited, with only a few works centered on factoid-based QuADs and none on non-factoid QuADs. Therefore, this work presents MuNfQuAD, a multilingual QuAD with non-factoid questions. It utilizes interrogative sub-headings from BBC news articles as questions and the corresponding paragraphs as silver answers. The dataset comprises over 578K QA pairs across 38 languages, encompass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10604","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/2408.10604/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":"2408.10604","created_at":"2026-07-05T10:16:58.849896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10604v2","created_at":"2026-07-05T10:16:58.849896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10604","created_at":"2026-07-05T10:16:58.849896+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODEO6OSGQF2R","created_at":"2026-07-05T10:16:58.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODEO6OSGQF2RL2BO","created_at":"2026-07-05T10:16:58.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODEO6OSG","created_at":"2026-07-05T10:16:58.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13615","citing_title":"Long-context Non-factoid Question Answering in Indic Languages","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM","json":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM.json","graph_json":"https://pith.science/api/pith-number/ODEO6OSGQF2RL2BO5YBRA2W3QM/graph.json","events_json":"https://pith.science/api/pith-number/ODEO6OSGQF2RL2BO5YBRA2W3QM/events.json","paper":"https://pith.science/paper/ODEO6OSG"},"agent_actions":{"view_html":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM","download_json":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM.json","view_paper":"https://pith.science/paper/ODEO6OSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10604&json=true","fetch_graph":"https://pith.science/api/pith-number/ODEO6OSGQF2RL2BO5YBRA2W3QM/graph.json","fetch_events":"https://pith.science/api/pith-number/ODEO6OSGQF2RL2BO5YBRA2W3QM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM/action/storage_attestation","attest_author":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM/action/author_attestation","sign_citation":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM/action/citation_signature","submit_replication":"https://pith.science/pith/ODEO6OSGQF2RL2BO5YBRA2W3QM/action/replication_record"}},"created_at":"2026-07-05T10:16:58.849896+00:00","updated_at":"2026-07-05T10:16:58.849896+00:00"}