{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3OS7OUUKZAF2HIESA4RZ45LSHQ","short_pith_number":"pith:3OS7OUUK","schema_version":"1.0","canonical_sha256":"dba5f7528ac80ba3a09207239e75723c2c46d0aee88d44a3e07b63f956729eb6","source":{"kind":"arxiv","id":"2103.08647","version":3},"attestation_state":"computed","paper":{"title":"The Effect of Domain and Diacritics in Yor\\`ub\\'a-English Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adesina Ayeni, Ayodele Awokoya, Cristina Espa\\~na-Bonet, Damilola Adebonojo, Dana Ruiter, David I. Adelani, Jesujoba O. Alabi, Mofe Adeyemi","submitted_at":"2021-03-15T18:52:32Z","abstract_excerpt":"Massively multilingual machine translation (MT) has shown impressive capabilities, including zero and few-shot translation between low-resource language pairs. However, these models are often evaluated on high-resource languages with the assumption that they generalize to low-resource ones. The difficulty of evaluating MT models on low-resource pairs is often due to lack of standardized evaluation datasets. In this paper, we present MENYO-20k, the first multi-domain parallel corpus with a special focus on clean orthography for Yor\\`ub\\'a--English with standardized train-test splits for benchma"},"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":"2103.08647","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-15T18:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"9bf18e7fbb6ceb3a5fc948657bbb88ac6c1904d39102bf7d328a655632d77d12","abstract_canon_sha256":"1c8985f227c350d1286124a2707d56e0ac530be082c08585ea62e3212897b3a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:48.222126Z","signature_b64":"2KV8Oa2nJqaMoyzScFxy3eF+NXZgDDzvT53MCasbJhH3X7IDopgj763DZlDcdj7jpqjPD9LHfwu1Al3uV+YoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba5f7528ac80ba3a09207239e75723c2c46d0aee88d44a3e07b63f956729eb6","last_reissued_at":"2026-07-05T03:05:48.221704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:48.221704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Effect of Domain and Diacritics in Yor\\`ub\\'a-English Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adesina Ayeni, Ayodele Awokoya, Cristina Espa\\~na-Bonet, Damilola Adebonojo, Dana Ruiter, David I. Adelani, Jesujoba O. Alabi, Mofe Adeyemi","submitted_at":"2021-03-15T18:52:32Z","abstract_excerpt":"Massively multilingual machine translation (MT) has shown impressive capabilities, including zero and few-shot translation between low-resource language pairs. However, these models are often evaluated on high-resource languages with the assumption that they generalize to low-resource ones. The difficulty of evaluating MT models on low-resource pairs is often due to lack of standardized evaluation datasets. In this paper, we present MENYO-20k, the first multi-domain parallel corpus with a special focus on clean orthography for Yor\\`ub\\'a--English with standardized train-test splits for benchma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08647","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/2103.08647/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":"2103.08647","created_at":"2026-07-05T03:05:48.221765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.08647v3","created_at":"2026-07-05T03:05:48.221765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08647","created_at":"2026-07-05T03:05:48.221765+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OS7OUUKZAF2","created_at":"2026-07-05T03:05:48.221765+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OS7OUUKZAF2HIES","created_at":"2026-07-05T03:05:48.221765+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OS7OUUK","created_at":"2026-07-05T03:05:48.221765+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/3OS7OUUKZAF2HIESA4RZ45LSHQ","json":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ.json","graph_json":"https://pith.science/api/pith-number/3OS7OUUKZAF2HIESA4RZ45LSHQ/graph.json","events_json":"https://pith.science/api/pith-number/3OS7OUUKZAF2HIESA4RZ45LSHQ/events.json","paper":"https://pith.science/paper/3OS7OUUK"},"agent_actions":{"view_html":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ","download_json":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ.json","view_paper":"https://pith.science/paper/3OS7OUUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.08647&json=true","fetch_graph":"https://pith.science/api/pith-number/3OS7OUUKZAF2HIESA4RZ45LSHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3OS7OUUKZAF2HIESA4RZ45LSHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/action/storage_attestation","attest_author":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/action/author_attestation","sign_citation":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/action/citation_signature","submit_replication":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/action/replication_record"}},"created_at":"2026-07-05T03:05:48.221765+00:00","updated_at":"2026-07-05T03:05:48.221765+00:00"}