{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KQZ7G46O44HTINAVBYBMXS2D4Z","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":"65aa8384393698c10ca8a949c23c04c399341131359caa71052892ef27422df5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T05:45:50Z","title_canon_sha256":"21b755e29e1652b6d5f46784d25d1ee22576d2fc47a15cb18627e4ccb42f9e14"},"schema_version":"1.0","source":{"id":"2210.11744","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11744","created_at":"2026-07-05T05:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11744v3","created_at":"2026-07-05T05:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11744","created_at":"2026-07-05T05:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"KQZ7G46O44HT","created_at":"2026-07-05T05:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"KQZ7G46O44HTINAV","created_at":"2026-07-05T05:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"KQZ7G46O","created_at":"2026-07-05T05:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:056689729c3d875e93d5e569ef29d178baddd514395a8e5ada4a80a09410b7a0","target":"graph","created_at":"2026-07-05T05:23:12Z","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/2210.11744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"AbdelRahim Elmadany, Alcides Alcoba Inciarte, Ife Adebara, Muhammad Abdul-Mageed","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T05:45:50Z","title":"AfroLID: A Neural Language Identification Tool for African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11744","kind":"arxiv","version":3},"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":"sha256:87b342e24f70a43ef5f5fa0d52625cf53e28745fa7fbf76262fd72102c2c6e93","target":"record","created_at":"2026-07-05T05:23:12Z","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":"65aa8384393698c10ca8a949c23c04c399341131359caa71052892ef27422df5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T05:45:50Z","title_canon_sha256":"21b755e29e1652b6d5f46784d25d1ee22576d2fc47a15cb18627e4ccb42f9e14"},"schema_version":"1.0","source":{"id":"2210.11744","kind":"arxiv","version":3}},"canonical_sha256":"5433f373cee70f3434150e02cbcb43e64acd52683dafdb20e776fafd720764da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5433f373cee70f3434150e02cbcb43e64acd52683dafdb20e776fafd720764da","first_computed_at":"2026-07-05T05:23:12.587245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:12.587245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dp72to+E9eZihiML4K0wGA95A9Mp3DsSx8TRsJhAbxsHWTIa04kMuWs/iYf7177CQ7cBAaajGC1sB/Cnk7LGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:12.587671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11744","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87b342e24f70a43ef5f5fa0d52625cf53e28745fa7fbf76262fd72102c2c6e93","sha256:056689729c3d875e93d5e569ef29d178baddd514395a8e5ada4a80a09410b7a0"],"state_sha256":"b07c3848b5790b8cbb8a895f54e379e3fc0b79d871a5ab6c5995f17b6d784dc4"}