{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NGK2C7YKATXL4PN2EBFJ5TTSTE","short_pith_number":"pith:NGK2C7YK","schema_version":"1.0","canonical_sha256":"6995a17f0a04eebe3dba204a9ece729923f9d6b33d7d643bc78b9be9c58047c9","source":{"kind":"arxiv","id":"2010.12174","version":1},"attestation_state":"computed","paper":{"title":"KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hong Qu, Julia Kreutzer, Li Huang, Rubungo Andre Niyongabo","submitted_at":"2020-10-23T05:37:42Z","abstract_excerpt":"Recent progress in text classification has been focused on high-resource languages such as English and Chinese. For low-resource languages, amongst them most African languages, the lack of well-annotated data and effective preprocessing, is hindering the progress and the transfer of successful methods. In this paper, we introduce two news datasets (KINNEWS and KIRNEWS) for multi-class classification of news articles in Kinyarwanda and Kirundi, two low-resource African languages. The two languages are mutually intelligible, but while Kinyarwanda has been studied in Natural Language Processing ("},"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":"2010.12174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T05:37:42Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"a0f2005a9c536fd5dd08c85c921e0ff90ac02d88586339bb596b8556efd60e1c","abstract_canon_sha256":"72c68db591d867e46d445b0ee6ea958a432c3fdf4e97fe8cc846649dfccd1d42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:34.552834Z","signature_b64":"ulBG8pHVXzuwYTdQFK0MhlRbu5AcIcK2ZyU/G9qASILCD+5NIJfQdkfG/fJVZ215xNhDR6OGeKXlY3GM+Nr6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6995a17f0a04eebe3dba204a9ece729923f9d6b33d7d643bc78b9be9c58047c9","last_reissued_at":"2026-07-05T01:45:34.552413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:34.552413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hong Qu, Julia Kreutzer, Li Huang, Rubungo Andre Niyongabo","submitted_at":"2020-10-23T05:37:42Z","abstract_excerpt":"Recent progress in text classification has been focused on high-resource languages such as English and Chinese. For low-resource languages, amongst them most African languages, the lack of well-annotated data and effective preprocessing, is hindering the progress and the transfer of successful methods. In this paper, we introduce two news datasets (KINNEWS and KIRNEWS) for multi-class classification of news articles in Kinyarwanda and Kirundi, two low-resource African languages. The two languages are mutually intelligible, but while Kinyarwanda has been studied in Natural Language Processing ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12174","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/2010.12174/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":"2010.12174","created_at":"2026-07-05T01:45:34.552477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12174v1","created_at":"2026-07-05T01:45:34.552477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12174","created_at":"2026-07-05T01:45:34.552477+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGK2C7YKATXL","created_at":"2026-07-05T01:45:34.552477+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGK2C7YKATXL4PN2","created_at":"2026-07-05T01:45:34.552477+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGK2C7YK","created_at":"2026-07-05T01:45:34.552477+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/NGK2C7YKATXL4PN2EBFJ5TTSTE","json":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE.json","graph_json":"https://pith.science/api/pith-number/NGK2C7YKATXL4PN2EBFJ5TTSTE/graph.json","events_json":"https://pith.science/api/pith-number/NGK2C7YKATXL4PN2EBFJ5TTSTE/events.json","paper":"https://pith.science/paper/NGK2C7YK"},"agent_actions":{"view_html":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE","download_json":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE.json","view_paper":"https://pith.science/paper/NGK2C7YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12174&json=true","fetch_graph":"https://pith.science/api/pith-number/NGK2C7YKATXL4PN2EBFJ5TTSTE/graph.json","fetch_events":"https://pith.science/api/pith-number/NGK2C7YKATXL4PN2EBFJ5TTSTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE/action/storage_attestation","attest_author":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE/action/author_attestation","sign_citation":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE/action/citation_signature","submit_replication":"https://pith.science/pith/NGK2C7YKATXL4PN2EBFJ5TTSTE/action/replication_record"}},"created_at":"2026-07-05T01:45:34.552477+00:00","updated_at":"2026-07-05T01:45:34.552477+00:00"}