{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R7RBKLJGDVWBUPBKFWMW55UJ54","short_pith_number":"pith:R7RBKLJG","schema_version":"1.0","canonical_sha256":"8fe2152d261d6c1a3c2a2d996ef689ef05133ab0d6428befdc01f0183d388853","source":{"kind":"arxiv","id":"2412.08279","version":1},"attestation_state":"computed","paper":{"title":"Y-NQ: English-Yor\\`ub\\'a Evaluation dataset for Open-Book Reading Comprehension and Text Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christophe Ropers, Eduardo S\\'anchez, Ifeoluwanimi Adebara, Joe Chuang, Joy Chen, Marta R. Costa-juss\\`a","submitted_at":"2024-12-11T10:52:29Z","abstract_excerpt":"The purpose of this work is to share an English-Yor\\`ub\\'a evaluation dataset for open-book reading comprehension and text generation to assess the performance of models both in a high- and a low- resource language. The dataset contains 358 questions and answers on 338 English documents and 208 Yor\\`ub\\'a documents. The average document length is ~ 10k words for English and 430 words for Yor\\`ub\\'a. Experiments show a consistent disparity in performance between the two languages, with Yor\\`ub\\'a falling behind English for automatic metrics even if documents are much shorter for this language. "},"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":"2412.08279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T10:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"63a8206c3db61ae06b72e8cbc0462ca59b4df9e6bd70aa69f228546797d8f3aa","abstract_canon_sha256":"71ed082f6e1be9ae81f8b176dccc57eadc27305dbe38a87395d849238bdf911b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:47.606928Z","signature_b64":"52qFTjgzaZ2yj/cBddPdLigkuWNO+2JKt9x1mZ4cmoqmGVcnglp9kEJLCGvmXZDkvDs/poO5Fjrx+vp0oKYyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe2152d261d6c1a3c2a2d996ef689ef05133ab0d6428befdc01f0183d388853","last_reissued_at":"2026-07-05T09:47:47.606399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:47.606399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Y-NQ: English-Yor\\`ub\\'a Evaluation dataset for Open-Book Reading Comprehension and Text Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christophe Ropers, Eduardo S\\'anchez, Ifeoluwanimi Adebara, Joe Chuang, Joy Chen, Marta R. Costa-juss\\`a","submitted_at":"2024-12-11T10:52:29Z","abstract_excerpt":"The purpose of this work is to share an English-Yor\\`ub\\'a evaluation dataset for open-book reading comprehension and text generation to assess the performance of models both in a high- and a low- resource language. The dataset contains 358 questions and answers on 338 English documents and 208 Yor\\`ub\\'a documents. The average document length is ~ 10k words for English and 430 words for Yor\\`ub\\'a. Experiments show a consistent disparity in performance between the two languages, with Yor\\`ub\\'a falling behind English for automatic metrics even if documents are much shorter for this language. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08279","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/2412.08279/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":"2412.08279","created_at":"2026-07-05T09:47:47.606451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08279v1","created_at":"2026-07-05T09:47:47.606451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08279","created_at":"2026-07-05T09:47:47.606451+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7RBKLJGDVWB","created_at":"2026-07-05T09:47:47.606451+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7RBKLJGDVWBUPBK","created_at":"2026-07-05T09:47:47.606451+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7RBKLJG","created_at":"2026-07-05T09:47:47.606451+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/R7RBKLJGDVWBUPBKFWMW55UJ54","json":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54.json","graph_json":"https://pith.science/api/pith-number/R7RBKLJGDVWBUPBKFWMW55UJ54/graph.json","events_json":"https://pith.science/api/pith-number/R7RBKLJGDVWBUPBKFWMW55UJ54/events.json","paper":"https://pith.science/paper/R7RBKLJG"},"agent_actions":{"view_html":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54","download_json":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54.json","view_paper":"https://pith.science/paper/R7RBKLJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08279&json=true","fetch_graph":"https://pith.science/api/pith-number/R7RBKLJGDVWBUPBKFWMW55UJ54/graph.json","fetch_events":"https://pith.science/api/pith-number/R7RBKLJGDVWBUPBKFWMW55UJ54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54/action/storage_attestation","attest_author":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54/action/author_attestation","sign_citation":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54/action/citation_signature","submit_replication":"https://pith.science/pith/R7RBKLJGDVWBUPBKFWMW55UJ54/action/replication_record"}},"created_at":"2026-07-05T09:47:47.606451+00:00","updated_at":"2026-07-05T09:47:47.606451+00:00"}