{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6C6HOCZOSWNIV3DETTXPJ55AHM","short_pith_number":"pith:6C6HOCZO","canonical_record":{"source":{"id":"2305.13989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"627be77100aedc9f2384c5b7c43d5259b726d5b379162845a9e49567a9af21b1","abstract_canon_sha256":"8a46f8b28facc172937041ac6cf444d14938330f3e32ab8200c0a9f841762728"},"schema_version":"1.0"},"canonical_sha256":"f0bc770b2e959a8aec649ceef4f7a03b1457407e40d7f3919fabffd5de890e1d","source":{"kind":"arxiv","id":"2305.13989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13989","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13989v1","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13989","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"6C6HOCZOSWNI","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"6C6HOCZOSWNIV3DE","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"6C6HOCZO","created_at":"2026-07-05T06:13:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6C6HOCZOSWNIV3DETTXPJ55AHM","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"627be77100aedc9f2384c5b7c43d5259b726d5b379162845a9e49567a9af21b1","abstract_canon_sha256":"8a46f8b28facc172937041ac6cf444d14938330f3e32ab8200c0a9f841762728"},"schema_version":"1.0"},"canonical_sha256":"f0bc770b2e959a8aec649ceef4f7a03b1457407e40d7f3919fabffd5de890e1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:00.023108Z","signature_b64":"cs+lWQIaakCxSV0TaoaNH+GMbuhBVzUZ/YPRykhRdfcjzAPBqs8iLCWBZBhZdyOapQlVmY80vzWB6F5Uop4VBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0bc770b2e959a8aec649ceef4f7a03b1457407e40d7f3919fabffd5de890e1d","last_reissued_at":"2026-07-05T06:13:00.022672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:00.022672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13989","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUtuwdf8bmJx0dubERzDwsf/Fqv2xSaC43YweyxP0X9xZIyBMeLW2pxhPlaivYHs7ijvanhgD0fk55M9xPsjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:27:11.146414Z"},"content_sha256":"d90b8bb8feaa1b7d17e6b932e3a26b43d7a473ec45cf2924f28fcf8688a7826b","schema_version":"1.0","event_id":"sha256:d90b8bb8feaa1b7d17e6b932e3a26b43d7a473ec45cf2924f28fcf8688a7826b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6C6HOCZOSWNIV3DETTXPJ55AHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aliyu Yusuf, Allahsera Auguste Tapo, Amelia Taylor, Andiswa Bukula, Anuoluwapo Aremu, Apelete Agbolo, Blessing Sibanda, Bonaventure F. P. Dossou, Catherine Gitau, Cheikh M. Bamba Dione, Chinedu Uchechukwu, Chris Chinenye Emezue, David Adelani, Derguene Mbaye, Dietrich Klakow, Edwin Munkoh-Buabeng, Emile Niyomutabazi, Ester Chimhenga, Fatoumata Ouoba Kabore, Godson Kalipe, Gratien Atindogbe, Happy Buzaaba, Idris Akinade, Ikechukwu Onyenwe, Jesujoba Alabi, Jonathan Mukiibi, Kudzai Gotosa, Marien Nahimana, Mboning Tchiaze Elvis, Muhammad Abdullahi, Olanrewaju Samuel, Patrick Mizha, Perez Ogayo, Peter Nabende, Rooweither Mabuya, Seydou Traore, Shamsuddeen Hassan Muhammad, Tajuddeen Gwadabe, Tebogo Macucwa, Thapelo Sindane, Th\\'eog\\`ene Musabeyezu, Tolulope Adelani, Victoire Memdjokam Koagne, Vukosi Marivate","submitted_at":"2023-05-23T12:15:33Z","abstract_excerpt":"In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13989","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/2305.13989/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":"2026-07-05T06:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lst4/drNj8X8rMvjZ5FeUS//RicQPlgw54Ckv8XJbVCj6W9Td8RT3MuCliyvOQ82ws9Rf4Iu5vLT/cEN9CIqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:27:11.146806Z"},"content_sha256":"c906df402c565199ad3e23a0e540a7b55b1cf57c649214a6ef76e49007435f1a","schema_version":"1.0","event_id":"sha256:c906df402c565199ad3e23a0e540a7b55b1cf57c649214a6ef76e49007435f1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6C6HOCZOSWNIV3DETTXPJ55AHM/bundle.json","state_url":"https://pith.science/pith/6C6HOCZOSWNIV3DETTXPJ55AHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6C6HOCZOSWNIV3DETTXPJ55AHM/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":"2026-07-08T16:27:11Z","links":{"resolver":"https://pith.science/pith/6C6HOCZOSWNIV3DETTXPJ55AHM","bundle":"https://pith.science/pith/6C6HOCZOSWNIV3DETTXPJ55AHM/bundle.json","state":"https://pith.science/pith/6C6HOCZOSWNIV3DETTXPJ55AHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6C6HOCZOSWNIV3DETTXPJ55AHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6C6HOCZOSWNIV3DETTXPJ55AHM","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":"8a46f8b28facc172937041ac6cf444d14938330f3e32ab8200c0a9f841762728","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:15:33Z","title_canon_sha256":"627be77100aedc9f2384c5b7c43d5259b726d5b379162845a9e49567a9af21b1"},"schema_version":"1.0","source":{"id":"2305.13989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13989","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13989v1","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13989","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"6C6HOCZOSWNI","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"6C6HOCZOSWNIV3DE","created_at":"2026-07-05T06:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"6C6HOCZO","created_at":"2026-07-05T06:13:00Z"}],"graph_snapshots":[{"event_id":"sha256:c906df402c565199ad3e23a0e540a7b55b1cf57c649214a6ef76e49007435f1a","target":"graph","created_at":"2026-07-05T06:13:00Z","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/2305.13989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatl","authors_text":"Aliyu Yusuf, Allahsera Auguste Tapo, Amelia Taylor, Andiswa Bukula, Anuoluwapo Aremu, Apelete Agbolo, Blessing Sibanda, Bonaventure F. P. Dossou, Catherine Gitau, Cheikh M. Bamba Dione, Chinedu Uchechukwu, Chris Chinenye Emezue, David Adelani, Derguene Mbaye, Dietrich Klakow, Edwin Munkoh-Buabeng, Emile Niyomutabazi, Ester Chimhenga, Fatoumata Ouoba Kabore, Godson Kalipe, Gratien Atindogbe, Happy Buzaaba, Idris Akinade, Ikechukwu Onyenwe, Jesujoba Alabi, Jonathan Mukiibi, Kudzai Gotosa, Marien Nahimana, Mboning Tchiaze Elvis, Muhammad Abdullahi, Olanrewaju Samuel, Patrick Mizha, Perez Ogayo, Peter Nabende, Rooweither Mabuya, Seydou Traore, Shamsuddeen Hassan Muhammad, Tajuddeen Gwadabe, Tebogo Macucwa, Thapelo Sindane, Th\\'eog\\`ene Musabeyezu, Tolulope Adelani, Victoire Memdjokam Koagne, Vukosi Marivate","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:15:33Z","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13989","kind":"arxiv","version":1},"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:d90b8bb8feaa1b7d17e6b932e3a26b43d7a473ec45cf2924f28fcf8688a7826b","target":"record","created_at":"2026-07-05T06:13:00Z","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":"8a46f8b28facc172937041ac6cf444d14938330f3e32ab8200c0a9f841762728","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:15:33Z","title_canon_sha256":"627be77100aedc9f2384c5b7c43d5259b726d5b379162845a9e49567a9af21b1"},"schema_version":"1.0","source":{"id":"2305.13989","kind":"arxiv","version":1}},"canonical_sha256":"f0bc770b2e959a8aec649ceef4f7a03b1457407e40d7f3919fabffd5de890e1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0bc770b2e959a8aec649ceef4f7a03b1457407e40d7f3919fabffd5de890e1d","first_computed_at":"2026-07-05T06:13:00.022672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:00.022672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cs+lWQIaakCxSV0TaoaNH+GMbuhBVzUZ/YPRykhRdfcjzAPBqs8iLCWBZBhZdyOapQlVmY80vzWB6F5Uop4VBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:00.023108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d90b8bb8feaa1b7d17e6b932e3a26b43d7a473ec45cf2924f28fcf8688a7826b","sha256:c906df402c565199ad3e23a0e540a7b55b1cf57c649214a6ef76e49007435f1a"],"state_sha256":"c424cdb22c0b7bcb93329abc2a3b4b554b2220dcd99f674883972c0c096cb3e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VsigMwjuENQ0ld5ajRqeEdE3R6zbE804Ssw2YGsHpK2V7vvJf4PcUmiuwrGEeYi5VftZBrwts8QAsB7Ks0vqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:27:11.148900Z","bundle_sha256":"9a8f433c114f551a0499ebe3d347287d9b28fd5ab39a6df972d2a9e6c5377ec4"}}