{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZPPFJHL5ZBNWB7GR4L4CIPF7OL","short_pith_number":"pith:ZPPFJHL5","schema_version":"1.0","canonical_sha256":"cbde549d7dc85b60fcd1e2f8243cbf72e0a127c44b1e33c470fd67d904af263a","source":{"kind":"arxiv","id":"2404.04809","version":1},"attestation_state":"computed","paper":{"title":"Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aso Mahmudi, Ekaterina Vylomova, Katrina Langford, Leo Alberto de Araujo, Rapha\\\"el Merx","submitted_at":"2024-04-07T05:04:38Z","abstract_excerpt":"This study explores the use of large language models (LLMs) for translating English into Mambai, a low-resource Austronesian language spoken in Timor-Leste, with approximately 200,000 native speakers. Leveraging a novel corpus derived from a Mambai language manual and additional sentences translated by a native speaker, we examine the efficacy of few-shot LLM prompting for machine translation (MT) in this low-resource context. Our methodology involves the strategic selection of parallel sentences and dictionary entries for prompting, aiming to enhance translation accuracy, using open-source an"},"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":"2404.04809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T05:04:38Z","cross_cats_sorted":[],"title_canon_sha256":"695ba60a818706f228d121c775069bd8ba94dceea0ebbcb74004a2fb4d9800f9","abstract_canon_sha256":"07150c5b5e8f4a5354c9e3873dcd099efcf56e31d4f472026b9aa06fce60eff0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:42.407677Z","signature_b64":"pbkd7t+Ax9j5xvPJsIaxzrmochaXYEVVCJRTfgWEngsJyr6BqqUFhYMfWX2WuADP4x8Th+T2PT3u8NUMpS5XCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbde549d7dc85b60fcd1e2f8243cbf72e0a127c44b1e33c470fd67d904af263a","last_reissued_at":"2026-07-05T10:05:42.407166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:42.407166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aso Mahmudi, Ekaterina Vylomova, Katrina Langford, Leo Alberto de Araujo, Rapha\\\"el Merx","submitted_at":"2024-04-07T05:04:38Z","abstract_excerpt":"This study explores the use of large language models (LLMs) for translating English into Mambai, a low-resource Austronesian language spoken in Timor-Leste, with approximately 200,000 native speakers. Leveraging a novel corpus derived from a Mambai language manual and additional sentences translated by a native speaker, we examine the efficacy of few-shot LLM prompting for machine translation (MT) in this low-resource context. Our methodology involves the strategic selection of parallel sentences and dictionary entries for prompting, aiming to enhance translation accuracy, using open-source an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04809","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/2404.04809/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":"2404.04809","created_at":"2026-07-05T10:05:42.407230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04809v1","created_at":"2026-07-05T10:05:42.407230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04809","created_at":"2026-07-05T10:05:42.407230+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPPFJHL5ZBNW","created_at":"2026-07-05T10:05:42.407230+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPPFJHL5ZBNWB7GR","created_at":"2026-07-05T10:05:42.407230+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPPFJHL5","created_at":"2026-07-05T10:05:42.407230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06420","citing_title":"A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL","json":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL.json","graph_json":"https://pith.science/api/pith-number/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/graph.json","events_json":"https://pith.science/api/pith-number/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/events.json","paper":"https://pith.science/paper/ZPPFJHL5"},"agent_actions":{"view_html":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL","download_json":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL.json","view_paper":"https://pith.science/paper/ZPPFJHL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04809&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/action/storage_attestation","attest_author":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/action/author_attestation","sign_citation":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/action/citation_signature","submit_replication":"https://pith.science/pith/ZPPFJHL5ZBNWB7GR4L4CIPF7OL/action/replication_record"}},"created_at":"2026-07-05T10:05:42.407230+00:00","updated_at":"2026-07-05T10:05:42.407230+00:00"}