{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UYSCPZLJLLFQLGKZ7CB7LS4PEK","short_pith_number":"pith:UYSCPZLJ","schema_version":"1.0","canonical_sha256":"a62427e5695acb059959f883f5cb8f229db85f9eca025a5452eb45f4ee6cf2fd","source":{"kind":"arxiv","id":"2307.00382","version":1},"attestation_state":"computed","paper":{"title":"Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Merel Scholman, Muhammed Saeed, Pin-Jie Lin","submitted_at":"2023-07-01T16:47:36Z","abstract_excerpt":"Developing effective spoken language processing systems for low-resource languages poses several challenges due to the lack of parallel data and limited resources for fine-tuning models. In this work, we target on improving upon both text classification and translation of Nigerian Pidgin (Naija) by collecting a large-scale parallel English-Pidgin corpus and further propose a framework of cross-lingual adaptive training that includes both continual and task adaptive training so as to adapt a base pre-trained model to low-resource languages. Our studies show that English pre-trained language mod"},"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":"2307.00382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-01T16:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"63afd2f659d2d7606a17b6af24e21b895347bb5ab0831f95859fd737e303690c","abstract_canon_sha256":"0766ac15ecc963bc902ace3e47db575322cf4ccce57da022c7cd1a513f5a69af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:55.515858Z","signature_b64":"PLnNzKriYKF9hYNfUnUJmI0EjuTrNJl+xusJdath68HiriqawZfQUH9kMpX4godkMBu5bBD+8tK3JxLKsrWkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62427e5695acb059959f883f5cb8f229db85f9eca025a5452eb45f4ee6cf2fd","last_reissued_at":"2026-07-05T06:26:55.515452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:55.515452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Merel Scholman, Muhammed Saeed, Pin-Jie Lin","submitted_at":"2023-07-01T16:47:36Z","abstract_excerpt":"Developing effective spoken language processing systems for low-resource languages poses several challenges due to the lack of parallel data and limited resources for fine-tuning models. In this work, we target on improving upon both text classification and translation of Nigerian Pidgin (Naija) by collecting a large-scale parallel English-Pidgin corpus and further propose a framework of cross-lingual adaptive training that includes both continual and task adaptive training so as to adapt a base pre-trained model to low-resource languages. Our studies show that English pre-trained language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00382","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/2307.00382/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":"2307.00382","created_at":"2026-07-05T06:26:55.515508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00382v1","created_at":"2026-07-05T06:26:55.515508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00382","created_at":"2026-07-05T06:26:55.515508+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYSCPZLJLLFQ","created_at":"2026-07-05T06:26:55.515508+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYSCPZLJLLFQLGKZ","created_at":"2026-07-05T06:26:55.515508+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYSCPZLJ","created_at":"2026-07-05T06:26:55.515508+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/UYSCPZLJLLFQLGKZ7CB7LS4PEK","json":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK.json","graph_json":"https://pith.science/api/pith-number/UYSCPZLJLLFQLGKZ7CB7LS4PEK/graph.json","events_json":"https://pith.science/api/pith-number/UYSCPZLJLLFQLGKZ7CB7LS4PEK/events.json","paper":"https://pith.science/paper/UYSCPZLJ"},"agent_actions":{"view_html":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK","download_json":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK.json","view_paper":"https://pith.science/paper/UYSCPZLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00382&json=true","fetch_graph":"https://pith.science/api/pith-number/UYSCPZLJLLFQLGKZ7CB7LS4PEK/graph.json","fetch_events":"https://pith.science/api/pith-number/UYSCPZLJLLFQLGKZ7CB7LS4PEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK/action/storage_attestation","attest_author":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK/action/author_attestation","sign_citation":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK/action/citation_signature","submit_replication":"https://pith.science/pith/UYSCPZLJLLFQLGKZ7CB7LS4PEK/action/replication_record"}},"created_at":"2026-07-05T06:26:55.515508+00:00","updated_at":"2026-07-05T06:26:55.515508+00:00"}