{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3OS7OUUKZAF2HIESA4RZ45LSHQ","short_pith_number":"pith:3OS7OUUK","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"},"canonical_sha256":"dba5f7528ac80ba3a09207239e75723c2c46d0aee88d44a3e07b63f956729eb6","source":{"kind":"arxiv","id":"2103.08647","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08647","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08647v3","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08647","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"3OS7OUUKZAF2","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"3OS7OUUKZAF2HIES","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"3OS7OUUK","created_at":"2026-07-05T03:05:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3OS7OUUKZAF2HIESA4RZ45LSHQ","target":"record","payload":{"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"},"canonical_sha256":"dba5f7528ac80ba3a09207239e75723c2c46d0aee88d44a3e07b63f956729eb6","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"},"source_kind":"arxiv","source_id":"2103.08647","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2Vgy/+vX+IsbQZCPY6NXvF2jUYAC/4IeMcnO5GFSd8od2VLl6LRdPHFefdDw7VkJIz6d77abxWhp6lGzPjlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:18:10.025279Z"},"content_sha256":"ec83d21f26b4ddabf1f0c23fa78771e4dfcc340bac38afe03888e157f4755789","schema_version":"1.0","event_id":"sha256:ec83d21f26b4ddabf1f0c23fa78771e4dfcc340bac38afe03888e157f4755789"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3OS7OUUKZAF2HIESA4RZ45LSHQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K61JOA8YUmxiGFQ8+Ay1X3oewb9+H6HNJXRug9fV4vL1nHFSpMOMGVFV3KSf8ky+3ME6EJb+HUwjYaL8lOvEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:18:10.025805Z"},"content_sha256":"5938318693a23cbd089282971c48f8bcb3d1b32fd429b51341c2dd619632ce7f","schema_version":"1.0","event_id":"sha256:5938318693a23cbd089282971c48f8bcb3d1b32fd429b51341c2dd619632ce7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/bundle.json","state_url":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T03:18:10Z","links":{"resolver":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ","bundle":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/bundle.json","state":"https://pith.science/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OS7OUUKZAF2HIESA4RZ45LSHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3OS7OUUKZAF2HIESA4RZ45LSHQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1c8985f227c350d1286124a2707d56e0ac530be082c08585ea62e3212897b3a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-15T18:52:32Z","title_canon_sha256":"9bf18e7fbb6ceb3a5fc948657bbb88ac6c1904d39102bf7d328a655632d77d12"},"schema_version":"1.0","source":{"id":"2103.08647","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08647","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08647v3","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08647","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"3OS7OUUKZAF2","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"3OS7OUUKZAF2HIES","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"3OS7OUUK","created_at":"2026-07-05T03:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:5938318693a23cbd089282971c48f8bcb3d1b32fd429b51341c2dd619632ce7f","target":"graph","created_at":"2026-07-05T03:05:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.08647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adesina Ayeni, Ayodele Awokoya, Cristina Espa\\~na-Bonet, Damilola Adebonojo, Dana Ruiter, David I. Adelani, Jesujoba O. Alabi, Mofe Adeyemi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-15T18:52:32Z","title":"The Effect of Domain and Diacritics in Yor\\`ub\\'a-English Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08647","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ec83d21f26b4ddabf1f0c23fa78771e4dfcc340bac38afe03888e157f4755789","target":"record","created_at":"2026-07-05T03:05:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1c8985f227c350d1286124a2707d56e0ac530be082c08585ea62e3212897b3a4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-15T18:52:32Z","title_canon_sha256":"9bf18e7fbb6ceb3a5fc948657bbb88ac6c1904d39102bf7d328a655632d77d12"},"schema_version":"1.0","source":{"id":"2103.08647","kind":"arxiv","version":3}},"canonical_sha256":"dba5f7528ac80ba3a09207239e75723c2c46d0aee88d44a3e07b63f956729eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dba5f7528ac80ba3a09207239e75723c2c46d0aee88d44a3e07b63f956729eb6","first_computed_at":"2026-07-05T03:05:48.221704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:48.221704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2KV8Oa2nJqaMoyzScFxy3eF+NXZgDDzvT53MCasbJhH3X7IDopgj763DZlDcdj7jpqjPD9LHfwu1Al3uV+YoCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:48.222126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08647","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec83d21f26b4ddabf1f0c23fa78771e4dfcc340bac38afe03888e157f4755789","sha256:5938318693a23cbd089282971c48f8bcb3d1b32fd429b51341c2dd619632ce7f"],"state_sha256":"729afb1c94c2bceb27c4c8b2e003e5697b8082dcc6b7fa7561ba35a72322c7b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z091txGZ/yHNCnfAuTm6gO9Fp6FxXnoW9BmUqb0paMSAEnZdyYHxehmHIrhTTY+2Z8azW6XLbyE4Nr6diPb7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:18:10.030207Z","bundle_sha256":"46565973d86ad5c49f8e3f7a71f9d2826e97893727c93bc9ccae9ef7d73293f3"}}