{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DMUJZMDY7VJ3RFUFIVKOC2ZLNH","short_pith_number":"pith:DMUJZMDY","schema_version":"1.0","canonical_sha256":"1b289cb078fd53b896854554e16b2b69e544173e5b0e9c50679587cfefb62bdc","source":{"kind":"arxiv","id":"2512.01557","version":3},"attestation_state":"computed","paper":{"title":"Language Diversity: Evaluating Language Usage and AI Performance on African Languages in Digital Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bekalu Tadele, Chukuemeka Edeh, Edward Ajayi, Eudoxie Umwari, Jules Udahemuka, Mawuli Deku, Prosper Singadi","submitted_at":"2025-12-01T11:27:13Z","abstract_excerpt":"This study examines the digital representation of African languages and the challenges this presents for current language detection tools. We evaluate their performance on Yoruba, Kinyarwanda, and Amharic. While these languages are spoken by millions, their online usage on conversational platforms is often sparse, heavily influenced by English, and not representative of the authentic, monolingual conversations prevalent among native speakers. This lack of readily available authentic data online creates a challenge of scarcity of conversational data for training language models. To investigate "},"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":"2512.01557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T11:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a616b1b7a1479673ae02028b10717ec2a8ef2049f7c63189c44662ade8fc305","abstract_canon_sha256":"eba4b3e5802b27eadc9d45cb7e0f11f77507afb0b0623399e5d2031b13b1f7c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b289cb078fd53b896854554e16b2b69e544173e5b0e9c50679587cfefb62bdc","last_reissued_at":"2026-07-31T01:32:58.701696Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:32:58.701696Z"},"graph_snapshot":{"paper":{"title":"Language Diversity: Evaluating Language Usage and AI Performance on African Languages in Digital Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bekalu Tadele, Chukuemeka Edeh, Edward Ajayi, Eudoxie Umwari, Jules Udahemuka, Mawuli Deku, Prosper Singadi","submitted_at":"2025-12-01T11:27:13Z","abstract_excerpt":"This study examines the digital representation of African languages and the challenges this presents for current language detection tools. We evaluate their performance on Yoruba, Kinyarwanda, and Amharic. While these languages are spoken by millions, their online usage on conversational platforms is often sparse, heavily influenced by English, and not representative of the authentic, monolingual conversations prevalent among native speakers. This lack of readily available authentic data online creates a challenge of scarcity of conversational data for training language models. To investigate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.01557","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/2512.01557/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":"2512.01557","created_at":"2026-07-31T01:32:58.704861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.01557v3","created_at":"2026-07-31T01:32:58.704861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.01557","created_at":"2026-07-31T01:32:58.704861+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMUJZMDY7VJ3","created_at":"2026-07-31T01:32:58.704861+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMUJZMDY7VJ3RFUF","created_at":"2026-07-31T01:32:58.704861+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMUJZMDY","created_at":"2026-07-31T01:32:58.704861+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/DMUJZMDY7VJ3RFUFIVKOC2ZLNH","json":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH.json","graph_json":"https://pith.science/api/pith-number/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/graph.json","events_json":"https://pith.science/api/pith-number/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/events.json","paper":"https://pith.science/paper/DMUJZMDY"},"agent_actions":{"view_html":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH","download_json":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH.json","view_paper":"https://pith.science/paper/DMUJZMDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.01557&json=true","fetch_graph":"https://pith.science/api/pith-number/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/graph.json","fetch_events":"https://pith.science/api/pith-number/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/action/storage_attestation","attest_author":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/action/author_attestation","sign_citation":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/action/citation_signature","submit_replication":"https://pith.science/pith/DMUJZMDY7VJ3RFUFIVKOC2ZLNH/action/replication_record"}},"created_at":"2026-07-31T01:32:58.704861+00:00","updated_at":"2026-07-31T01:32:58.704861+00:00"}