{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T25WVEFIDHF5GGC4UGG7BCTNOD","short_pith_number":"pith:T25WVEFI","schema_version":"1.0","canonical_sha256":"9ebb6a90a819cbd3185ca18df08a6d70ced756cf5cf830c54e743ddc6f2dee4f","source":{"kind":"arxiv","id":"2505.18905","version":1},"attestation_state":"computed","paper":{"title":"Building a Functional Machine Translation Corpus for Kpelle","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emmanuel J. Dorley, Jackson Weako, Kweku Andoh Yamoah","submitted_at":"2025-05-24T23:39:34Z","abstract_excerpt":"In this paper, we introduce the first publicly available English-Kpelle dataset for machine translation, comprising over 2000 sentence pairs drawn from everyday communication, religious texts, and educational materials. By fine-tuning Meta's No Language Left Behind(NLLB) model on two versions of the dataset, we achieved BLEU scores of up to 30 in the Kpelle-to-English direction, demonstrating the benefits of data augmentation. Our findings align with NLLB-200 benchmarks on other African languages, underscoring Kpelle's potential for competitive performance despite its low-resource status. Beyo"},"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":"2505.18905","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T23:39:34Z","cross_cats_sorted":[],"title_canon_sha256":"00fc5896c659e2bbc95e3ee227a58939c707e9dc94344a95fcc818a6de1a23fb","abstract_canon_sha256":"575a55f0fd6a09e65c777e8ca9b37d419780acd59e00ae2f175ee58693a4e69b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:21.654734Z","signature_b64":"ulUWQ8F2KT/LMEDA5Qvjv21VW0k8fbpEp3dzdO1eHt/vxk0g1QHE1Uafz1dc5cbTFV+jl6JFDt28T9G4t2XCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ebb6a90a819cbd3185ca18df08a6d70ced756cf5cf830c54e743ddc6f2dee4f","last_reissued_at":"2026-07-05T11:09:21.654247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:21.654247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building a Functional Machine Translation Corpus for Kpelle","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emmanuel J. Dorley, Jackson Weako, Kweku Andoh Yamoah","submitted_at":"2025-05-24T23:39:34Z","abstract_excerpt":"In this paper, we introduce the first publicly available English-Kpelle dataset for machine translation, comprising over 2000 sentence pairs drawn from everyday communication, religious texts, and educational materials. By fine-tuning Meta's No Language Left Behind(NLLB) model on two versions of the dataset, we achieved BLEU scores of up to 30 in the Kpelle-to-English direction, demonstrating the benefits of data augmentation. Our findings align with NLLB-200 benchmarks on other African languages, underscoring Kpelle's potential for competitive performance despite its low-resource status. Beyo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18905","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/2505.18905/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":"2505.18905","created_at":"2026-07-05T11:09:21.654306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18905v1","created_at":"2026-07-05T11:09:21.654306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18905","created_at":"2026-07-05T11:09:21.654306+00:00"},{"alias_kind":"pith_short_12","alias_value":"T25WVEFIDHF5","created_at":"2026-07-05T11:09:21.654306+00:00"},{"alias_kind":"pith_short_16","alias_value":"T25WVEFIDHF5GGC4","created_at":"2026-07-05T11:09:21.654306+00:00"},{"alias_kind":"pith_short_8","alias_value":"T25WVEFI","created_at":"2026-07-05T11:09:21.654306+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/T25WVEFIDHF5GGC4UGG7BCTNOD","json":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD.json","graph_json":"https://pith.science/api/pith-number/T25WVEFIDHF5GGC4UGG7BCTNOD/graph.json","events_json":"https://pith.science/api/pith-number/T25WVEFIDHF5GGC4UGG7BCTNOD/events.json","paper":"https://pith.science/paper/T25WVEFI"},"agent_actions":{"view_html":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD","download_json":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD.json","view_paper":"https://pith.science/paper/T25WVEFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18905&json=true","fetch_graph":"https://pith.science/api/pith-number/T25WVEFIDHF5GGC4UGG7BCTNOD/graph.json","fetch_events":"https://pith.science/api/pith-number/T25WVEFIDHF5GGC4UGG7BCTNOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD/action/storage_attestation","attest_author":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD/action/author_attestation","sign_citation":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD/action/citation_signature","submit_replication":"https://pith.science/pith/T25WVEFIDHF5GGC4UGG7BCTNOD/action/replication_record"}},"created_at":"2026-07-05T11:09:21.654306+00:00","updated_at":"2026-07-05T11:09:21.654306+00:00"}