{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BKE2GVXVNAHQGRS5LLA62XS4PP","short_pith_number":"pith:BKE2GVXV","schema_version":"1.0","canonical_sha256":"0a89a356f5680f03465d5ac1ed5e5c7be657c5a965e644ee2436be30108ed136","source":{"kind":"arxiv","id":"2404.17216","version":1},"attestation_state":"computed","paper":{"title":"Prompting Towards Alleviating Code-Switched Data Scarcity in Under-Resourced Languages with GPT as a Pivot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kayode Olaleye, Michelle Terblanche, Vukosi Marivate","submitted_at":"2024-04-26T07:44:44Z","abstract_excerpt":"Many multilingual communities, including numerous in Africa, frequently engage in code-switching during conversations. This behaviour stresses the need for natural language processing technologies adept at processing code-switched text. However, data scarcity, particularly in African languages, poses a significant challenge, as many are low-resourced and under-represented. In this study, we prompted GPT 3.5 to generate Afrikaans--English and Yoruba--English code-switched sentences, enhancing diversity using topic-keyword pairs, linguistic guidelines, and few-shot examples. Our findings indicat"},"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":"2404.17216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T07:44:44Z","cross_cats_sorted":[],"title_canon_sha256":"4a7e55da1fa270e5273c9b7e2953eca330156c5339766eeba427385d80fabc58","abstract_canon_sha256":"ba10fe9a67c6cf909fef36b9ca6c6cdd70f794a826f0ca0386d91a51efdb91a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:34.775562Z","signature_b64":"hczb/Qe+BD6Bmw8D2XNel5J3Z3wcFOAqQlXrVAdflySnmChJUHptXawIHjY4s+nffrsABk6Ml2qm9kMFKYQNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a89a356f5680f03465d5ac1ed5e5c7be657c5a965e644ee2436be30108ed136","last_reissued_at":"2026-07-05T08:12:34.775119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:34.775119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Towards Alleviating Code-Switched Data Scarcity in Under-Resourced Languages with GPT as a Pivot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kayode Olaleye, Michelle Terblanche, Vukosi Marivate","submitted_at":"2024-04-26T07:44:44Z","abstract_excerpt":"Many multilingual communities, including numerous in Africa, frequently engage in code-switching during conversations. This behaviour stresses the need for natural language processing technologies adept at processing code-switched text. However, data scarcity, particularly in African languages, poses a significant challenge, as many are low-resourced and under-represented. In this study, we prompted GPT 3.5 to generate Afrikaans--English and Yoruba--English code-switched sentences, enhancing diversity using topic-keyword pairs, linguistic guidelines, and few-shot examples. Our findings indicat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17216","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/2404.17216/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":"2404.17216","created_at":"2026-07-05T08:12:34.775174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17216v1","created_at":"2026-07-05T08:12:34.775174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17216","created_at":"2026-07-05T08:12:34.775174+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKE2GVXVNAHQ","created_at":"2026-07-05T08:12:34.775174+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKE2GVXVNAHQGRS5","created_at":"2026-07-05T08:12:34.775174+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKE2GVXV","created_at":"2026-07-05T08:12:34.775174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06180","citing_title":"RideKE: Leveraging Low-Resource, User-Generated Twitter Content for Sentiment and Emotion Detection in Kenyan Code-Switched Dataset","ref_index":136,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP","json":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP.json","graph_json":"https://pith.science/api/pith-number/BKE2GVXVNAHQGRS5LLA62XS4PP/graph.json","events_json":"https://pith.science/api/pith-number/BKE2GVXVNAHQGRS5LLA62XS4PP/events.json","paper":"https://pith.science/paper/BKE2GVXV"},"agent_actions":{"view_html":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP","download_json":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP.json","view_paper":"https://pith.science/paper/BKE2GVXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17216&json=true","fetch_graph":"https://pith.science/api/pith-number/BKE2GVXVNAHQGRS5LLA62XS4PP/graph.json","fetch_events":"https://pith.science/api/pith-number/BKE2GVXVNAHQGRS5LLA62XS4PP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP/action/storage_attestation","attest_author":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP/action/author_attestation","sign_citation":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP/action/citation_signature","submit_replication":"https://pith.science/pith/BKE2GVXVNAHQGRS5LLA62XS4PP/action/replication_record"}},"created_at":"2026-07-05T08:12:34.775174+00:00","updated_at":"2026-07-05T08:12:34.775174+00:00"}