{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:R3NHZ52DGOPHXLND4KBTS7IRLR","short_pith_number":"pith:R3NHZ52D","canonical_record":{"source":{"id":"2205.02022","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T12:11:47Z","cross_cats_sorted":[],"title_canon_sha256":"0f0c842701356d32025833c7186c005e5a2d11b782009cc018759d4d66b5d228","abstract_canon_sha256":"6045dcac5cdbabcf1f90d4a5dc987c6613153db5d8f4aa85d155a33827d839bd"},"schema_version":"1.0"},"canonical_sha256":"8eda7cf743339e7bada3e283397d115c47579b4b9b71c771abf473e456af13e2","source":{"kind":"arxiv","id":"2205.02022","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02022","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02022v2","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02022","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"pith_short_12","alias_value":"R3NHZ52DGOPH","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"pith_short_16","alias_value":"R3NHZ52DGOPHXLND","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"pith_short_8","alias_value":"R3NHZ52D","created_at":"2026-07-05T04:50:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:R3NHZ52DGOPHXLND4KBTS7IRLR","target":"record","payload":{"canonical_record":{"source":{"id":"2205.02022","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T12:11:47Z","cross_cats_sorted":[],"title_canon_sha256":"0f0c842701356d32025833c7186c005e5a2d11b782009cc018759d4d66b5d228","abstract_canon_sha256":"6045dcac5cdbabcf1f90d4a5dc987c6613153db5d8f4aa85d155a33827d839bd"},"schema_version":"1.0"},"canonical_sha256":"8eda7cf743339e7bada3e283397d115c47579b4b9b71c771abf473e456af13e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:16.947293Z","signature_b64":"2ErjXTcOVWpz5j04maM0D6+uUAxCWQ3Nb93Cwl0jsORtxV3mAcTb9n/LWZEkktQx8o3sgmfKa1MkgB57uC2mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eda7cf743339e7bada3e283397d115c47579b4b9b71c771abf473e456af13e2","last_reissued_at":"2026-07-05T04:50:16.946891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:16.946891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.02022","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:50:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XdVNk+qvaWKDhqJKCWJezNZZKdzMbae6Nhm3XBvd1vPItHwkfQE7gTGIsDlpnuIHpG1JD4PlZmypEtrKaxDdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:16:49.507234Z"},"content_sha256":"fb58429d133a1d0e2cea2797929899d591d01b1311e8888d234a3903c447d0d8","schema_version":"1.0","event_id":"sha256:fb58429d133a1d0e2cea2797929899d591d01b1311e8888d234a3903c447d0d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:R3NHZ52DGOPHXLND4KBTS7IRLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Allahsera Auguste Tapo, Andiswa Bukula, Andre Niyongabo Rubungo, Angela Fan, Anuoluwapo Aremu, Ayodele Awokoya, Benjamin Ayoade Ajibade, Blessing Sibanda, Bonaventure F. P. Dossou, Chris Chinenye Emezue, Colin Leong, Dana Ruiter, David Ifeoluwa Adelani, Derguene Mbaye, Dietrich Klakow, Edwin Munkoh-Buabeng, Eric Peter Wairagala, Ernie Chang, Fatoumata Ouoba Kabore, Freshia Sackey, Gilles Hacheme, Godson Koffi Kalipe, Guyo Dub Jarso, Happy Buzaaba, Idris Abdulmumin, Jade Abbott, Jesujoba Oluwadara Alabi, Jonathan Mukiibi, Julia Kreutzer, Machel Reid, Michael Beukman, Millicent Ochieng, Mohamed Ahmed, Muhammad Umair Nasir, Oreen Yousuf, Perez Ogayo, Peter Nabende, Sam Manthalu, Shamsuddeen Hassan Muhammad, Tajuddeen Gwadabe, Tunde Oluwaseyi Ajayi, Valencia Wagner, Victoire Memdjokam Koagne, Xiaoyu Shen, Yvonne Wambui Gitau","submitted_at":"2022-05-04T12:11:47Z","abstract_excerpt":"Recent advances in the pre-training of language models leverage large-scale datasets to create multilingual models. However, low-resource languages are mostly left out in these datasets. This is primarily because many widely spoken languages are not well represented on the web and therefore excluded from the large-scale crawls used to create datasets. Furthermore, downstream users of these models are restricted to the selection of languages originally chosen for pre-training. This work investigates how to optimally leverage existing pre-trained models to create low-resource translation systems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02022","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/2205.02022/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":"2026-07-05T04:50:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AqCQhmldJ3yDvx7ZAQ9PDeqjPXTvrRCsL7UK90AO61da48HjDJjcP+DoBdMkV4ngCQrON9IzeNh/nFm5lUPcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:16:49.507682Z"},"content_sha256":"568abf3b419ca30d0db389daa76b87f387a9224f4ef0db43e6e52d17620b6bf4","schema_version":"1.0","event_id":"sha256:568abf3b419ca30d0db389daa76b87f387a9224f4ef0db43e6e52d17620b6bf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3NHZ52DGOPHXLND4KBTS7IRLR/bundle.json","state_url":"https://pith.science/pith/R3NHZ52DGOPHXLND4KBTS7IRLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3NHZ52DGOPHXLND4KBTS7IRLR/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":"2026-07-08T17:16:49Z","links":{"resolver":"https://pith.science/pith/R3NHZ52DGOPHXLND4KBTS7IRLR","bundle":"https://pith.science/pith/R3NHZ52DGOPHXLND4KBTS7IRLR/bundle.json","state":"https://pith.science/pith/R3NHZ52DGOPHXLND4KBTS7IRLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3NHZ52DGOPHXLND4KBTS7IRLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R3NHZ52DGOPHXLND4KBTS7IRLR","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":"6045dcac5cdbabcf1f90d4a5dc987c6613153db5d8f4aa85d155a33827d839bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T12:11:47Z","title_canon_sha256":"0f0c842701356d32025833c7186c005e5a2d11b782009cc018759d4d66b5d228"},"schema_version":"1.0","source":{"id":"2205.02022","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02022","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02022v2","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02022","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"pith_short_12","alias_value":"R3NHZ52DGOPH","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"pith_short_16","alias_value":"R3NHZ52DGOPHXLND","created_at":"2026-07-05T04:50:16Z"},{"alias_kind":"pith_short_8","alias_value":"R3NHZ52D","created_at":"2026-07-05T04:50:16Z"}],"graph_snapshots":[{"event_id":"sha256:568abf3b419ca30d0db389daa76b87f387a9224f4ef0db43e6e52d17620b6bf4","target":"graph","created_at":"2026-07-05T04:50:16Z","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/2205.02022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in the pre-training of language models leverage large-scale datasets to create multilingual models. However, low-resource languages are mostly left out in these datasets. This is primarily because many widely spoken languages are not well represented on the web and therefore excluded from the large-scale crawls used to create datasets. Furthermore, downstream users of these models are restricted to the selection of languages originally chosen for pre-training. This work investigates how to optimally leverage existing pre-trained models to create low-resource translation systems","authors_text":"Allahsera Auguste Tapo, Andiswa Bukula, Andre Niyongabo Rubungo, Angela Fan, Anuoluwapo Aremu, Ayodele Awokoya, Benjamin Ayoade Ajibade, Blessing Sibanda, Bonaventure F. P. Dossou, Chris Chinenye Emezue, Colin Leong, Dana Ruiter, David Ifeoluwa Adelani, Derguene Mbaye, Dietrich Klakow, Edwin Munkoh-Buabeng, Eric Peter Wairagala, Ernie Chang, Fatoumata Ouoba Kabore, Freshia Sackey, Gilles Hacheme, Godson Koffi Kalipe, Guyo Dub Jarso, Happy Buzaaba, Idris Abdulmumin, Jade Abbott, Jesujoba Oluwadara Alabi, Jonathan Mukiibi, Julia Kreutzer, Machel Reid, Michael Beukman, Millicent Ochieng, Mohamed Ahmed, Muhammad Umair Nasir, Oreen Yousuf, Perez Ogayo, Peter Nabende, Sam Manthalu, Shamsuddeen Hassan Muhammad, Tajuddeen Gwadabe, Tunde Oluwaseyi Ajayi, Valencia Wagner, Victoire Memdjokam Koagne, Xiaoyu Shen, Yvonne Wambui Gitau","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T12:11:47Z","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02022","kind":"arxiv","version":2},"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:fb58429d133a1d0e2cea2797929899d591d01b1311e8888d234a3903c447d0d8","target":"record","created_at":"2026-07-05T04:50:16Z","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":"6045dcac5cdbabcf1f90d4a5dc987c6613153db5d8f4aa85d155a33827d839bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T12:11:47Z","title_canon_sha256":"0f0c842701356d32025833c7186c005e5a2d11b782009cc018759d4d66b5d228"},"schema_version":"1.0","source":{"id":"2205.02022","kind":"arxiv","version":2}},"canonical_sha256":"8eda7cf743339e7bada3e283397d115c47579b4b9b71c771abf473e456af13e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eda7cf743339e7bada3e283397d115c47579b4b9b71c771abf473e456af13e2","first_computed_at":"2026-07-05T04:50:16.946891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:50:16.946891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2ErjXTcOVWpz5j04maM0D6+uUAxCWQ3Nb93Cwl0jsORtxV3mAcTb9n/LWZEkktQx8o3sgmfKa1MkgB57uC2mBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:50:16.947293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02022","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb58429d133a1d0e2cea2797929899d591d01b1311e8888d234a3903c447d0d8","sha256:568abf3b419ca30d0db389daa76b87f387a9224f4ef0db43e6e52d17620b6bf4"],"state_sha256":"04f72455640abb9d7ed06acb5c9fc10844351652b80309436b249a1ac666a83f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O87M8QQJdsPIow4/+nUeZRGkdMaXRtzuRQcB+i7D0P1e12gSwMhqtG58puS2DP7KV8S9ycEEy+4Gmk0K5E7mAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T17:16:49.511782Z","bundle_sha256":"6b8cdd48e93516f04b535ce86b5a08b1103a3527945d7af8b9e63863865352a1"}}