{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KQZ7G46O44HTINAVBYBMXS2D4Z","short_pith_number":"pith:KQZ7G46O","schema_version":"1.0","canonical_sha256":"5433f373cee70f3434150e02cbcb43e64acd52683dafdb20e776fafd720764da","source":{"kind":"arxiv","id":"2210.11744","version":3},"attestation_state":"computed","paper":{"title":"AfroLID: A Neural Language Identification Tool for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Alcides Alcoba Inciarte, Ife Adebara, Muhammad Abdul-Mageed","submitted_at":"2022-10-21T05:45:50Z","abstract_excerpt":"Language identification (LID) is a crucial precursor for NLP, especially for mining web data. Problematically, most of the world's 7000+ languages today are not covered by LID technologies. We address this pressing issue for Africa by introducing AfroLID, a neural LID toolkit for $517$ African languages and varieties. AfroLID exploits a multi-domain web dataset manually curated from across 14 language families utilizing five orthographic systems. When evaluated on our blind Test set, AfroLID achieves 95.89 F_1-score. We also compare AfroLID to five existing LID tools that each cover a small nu"},"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":"2210.11744","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T05:45:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"21b755e29e1652b6d5f46784d25d1ee22576d2fc47a15cb18627e4ccb42f9e14","abstract_canon_sha256":"65aa8384393698c10ca8a949c23c04c399341131359caa71052892ef27422df5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:12.587671Z","signature_b64":"dp72to+E9eZihiML4K0wGA95A9Mp3DsSx8TRsJhAbxsHWTIa04kMuWs/iYf7177CQ7cBAaajGC1sB/Cnk7LGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5433f373cee70f3434150e02cbcb43e64acd52683dafdb20e776fafd720764da","last_reissued_at":"2026-07-05T05:23:12.587245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:12.587245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AfroLID: A Neural Language Identification Tool for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Alcides Alcoba Inciarte, Ife Adebara, Muhammad Abdul-Mageed","submitted_at":"2022-10-21T05:45:50Z","abstract_excerpt":"Language identification (LID) is a crucial precursor for NLP, especially for mining web data. Problematically, most of the world's 7000+ languages today are not covered by LID technologies. We address this pressing issue for Africa by introducing AfroLID, a neural LID toolkit for $517$ African languages and varieties. AfroLID exploits a multi-domain web dataset manually curated from across 14 language families utilizing five orthographic systems. When evaluated on our blind Test set, AfroLID achieves 95.89 F_1-score. We also compare AfroLID to five existing LID tools that each cover a small nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11744","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/2210.11744/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":"2210.11744","created_at":"2026-07-05T05:23:12.587320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11744v3","created_at":"2026-07-05T05:23:12.587320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11744","created_at":"2026-07-05T05:23:12.587320+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQZ7G46O44HT","created_at":"2026-07-05T05:23:12.587320+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQZ7G46O44HTINAV","created_at":"2026-07-05T05:23:12.587320+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQZ7G46O","created_at":"2026-07-05T05:23:12.587320+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/KQZ7G46O44HTINAVBYBMXS2D4Z","json":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z.json","graph_json":"https://pith.science/api/pith-number/KQZ7G46O44HTINAVBYBMXS2D4Z/graph.json","events_json":"https://pith.science/api/pith-number/KQZ7G46O44HTINAVBYBMXS2D4Z/events.json","paper":"https://pith.science/paper/KQZ7G46O"},"agent_actions":{"view_html":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z","download_json":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z.json","view_paper":"https://pith.science/paper/KQZ7G46O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11744&json=true","fetch_graph":"https://pith.science/api/pith-number/KQZ7G46O44HTINAVBYBMXS2D4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KQZ7G46O44HTINAVBYBMXS2D4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z/action/storage_attestation","attest_author":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z/action/author_attestation","sign_citation":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z/action/citation_signature","submit_replication":"https://pith.science/pith/KQZ7G46O44HTINAVBYBMXS2D4Z/action/replication_record"}},"created_at":"2026-07-05T05:23:12.587320+00:00","updated_at":"2026-07-05T05:23:12.587320+00:00"}