{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QEM64T2HO2JBUIJWFEXE7JT6AO","short_pith_number":"pith:QEM64T2H","schema_version":"1.0","canonical_sha256":"8119ee4f4776921a2136292e4fa67e038faae42f410f65d2363a949dcccf15d9","source":{"kind":"arxiv","id":"2404.04212","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Guzm\\'an, En-Shiun Annie Lee, Sarubi Thillainathan, Surangika Ranathunga, Tong Su, Xin Peng","submitted_at":"2024-04-05T16:42:28Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency. They are important in Low-Resource Language (LRL) Neural Machine Translation (NMT) to enhance translation accuracy with minimal resources. However, their practical effectiveness varies significantly across different languages. We conducted comprehensive empirical experiments with varying LRL domains and sizes to evaluate the performance of 8 PEFT methods with in total of 15 architecture"},"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":"2404.04212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T16:42:28Z","cross_cats_sorted":[],"title_canon_sha256":"5ace94f518a16659de509136943a677a9345bd751b493af0f454ef81f8ace25e","abstract_canon_sha256":"af53fc515048ebeaf1d32f6085760fd01ea7312a2539630db65cfda81bf2b814"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:47.089599Z","signature_b64":"Zx+f9ZFHaBXL3ERC7e+GVEWfhPJg9Ou0QPv/lb7uRa3P3Mabs9Xox3GR6ndS/oTw3/0z20JUQJC+4Ic790iwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8119ee4f4776921a2136292e4fa67e038faae42f410f65d2363a949dcccf15d9","last_reissued_at":"2026-07-05T08:04:47.089148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:47.089148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Guzm\\'an, En-Shiun Annie Lee, Sarubi Thillainathan, Surangika Ranathunga, Tong Su, Xin Peng","submitted_at":"2024-04-05T16:42:28Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency. They are important in Low-Resource Language (LRL) Neural Machine Translation (NMT) to enhance translation accuracy with minimal resources. However, their practical effectiveness varies significantly across different languages. We conducted comprehensive empirical experiments with varying LRL domains and sizes to evaluate the performance of 8 PEFT methods with in total of 15 architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04212","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/2404.04212/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":"2404.04212","created_at":"2026-07-05T08:04:47.089207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04212v1","created_at":"2026-07-05T08:04:47.089207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04212","created_at":"2026-07-05T08:04:47.089207+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEM64T2HO2JB","created_at":"2026-07-05T08:04:47.089207+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEM64T2HO2JBUIJW","created_at":"2026-07-05T08:04:47.089207+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEM64T2H","created_at":"2026-07-05T08:04:47.089207+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/QEM64T2HO2JBUIJWFEXE7JT6AO","json":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO.json","graph_json":"https://pith.science/api/pith-number/QEM64T2HO2JBUIJWFEXE7JT6AO/graph.json","events_json":"https://pith.science/api/pith-number/QEM64T2HO2JBUIJWFEXE7JT6AO/events.json","paper":"https://pith.science/paper/QEM64T2H"},"agent_actions":{"view_html":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO","download_json":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO.json","view_paper":"https://pith.science/paper/QEM64T2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04212&json=true","fetch_graph":"https://pith.science/api/pith-number/QEM64T2HO2JBUIJWFEXE7JT6AO/graph.json","fetch_events":"https://pith.science/api/pith-number/QEM64T2HO2JBUIJWFEXE7JT6AO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO/action/storage_attestation","attest_author":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO/action/author_attestation","sign_citation":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO/action/citation_signature","submit_replication":"https://pith.science/pith/QEM64T2HO2JBUIJWFEXE7JT6AO/action/replication_record"}},"created_at":"2026-07-05T08:04:47.089207+00:00","updated_at":"2026-07-05T08:04:47.089207+00:00"}