{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:42245LDJN32NHVDRNG3L524IQL","short_pith_number":"pith:42245LDJ","schema_version":"1.0","canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","source":{"kind":"arxiv","id":"2507.00297","version":1},"attestation_state":"computed","paper":{"title":"Natural language processing for African languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani","submitted_at":"2025-06-30T22:26:36Z","abstract_excerpt":"Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the indigenous languages in this region can be regarded as low-resourced in terms of the availability of "},"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":"2507.00297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T22:26:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64363b17ba53b409de1052a8464c915b1bc9c0e503bfce6461b643469334b2b0","abstract_canon_sha256":"35f90930e6732a1d9b4c856a007f106d4dc9b365d7382367c540a66cdaec296c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:05.722767Z","signature_b64":"Px8slc+ulo8CFyoYeYpSTP7nwdqOh5g5agwjyJQt2aRQmIvrhE/9ecVr0nB64Cr6yIoX61h/ATrdR7dUZPbICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","last_reissued_at":"2026-07-05T11:30:05.722394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:05.722394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural language processing for African languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani","submitted_at":"2025-06-30T22:26:36Z","abstract_excerpt":"Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the indigenous languages in this region can be regarded as low-resourced in terms of the availability of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00297","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/2507.00297/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":"2507.00297","created_at":"2026-07-05T11:30:05.722457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00297v1","created_at":"2026-07-05T11:30:05.722457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00297","created_at":"2026-07-05T11:30:05.722457+00:00"},{"alias_kind":"pith_short_12","alias_value":"42245LDJN32N","created_at":"2026-07-05T11:30:05.722457+00:00"},{"alias_kind":"pith_short_16","alias_value":"42245LDJN32NHVDR","created_at":"2026-07-05T11:30:05.722457+00:00"},{"alias_kind":"pith_short_8","alias_value":"42245LDJ","created_at":"2026-07-05T11:30:05.722457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02608","citing_title":"Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL","json":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL.json","graph_json":"https://pith.science/api/pith-number/42245LDJN32NHVDRNG3L524IQL/graph.json","events_json":"https://pith.science/api/pith-number/42245LDJN32NHVDRNG3L524IQL/events.json","paper":"https://pith.science/paper/42245LDJ"},"agent_actions":{"view_html":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL","download_json":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL.json","view_paper":"https://pith.science/paper/42245LDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00297&json=true","fetch_graph":"https://pith.science/api/pith-number/42245LDJN32NHVDRNG3L524IQL/graph.json","fetch_events":"https://pith.science/api/pith-number/42245LDJN32NHVDRNG3L524IQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/action/storage_attestation","attest_author":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/action/author_attestation","sign_citation":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/action/citation_signature","submit_replication":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/action/replication_record"}},"created_at":"2026-07-05T11:30:05.722457+00:00","updated_at":"2026-07-05T11:30:05.722457+00:00"}