{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QPNPROMNUVFXV5Y6BDDVDXJT7Y","short_pith_number":"pith:QPNPROMN","schema_version":"1.0","canonical_sha256":"83daf8b98da54b7af71e08c751dd33fe0b0cae1da060e649ae8bd8d4d25eb8d9","source":{"kind":"arxiv","id":"2402.02633","version":1},"attestation_state":"computed","paper":{"title":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"A. Seza Do\\u{g}ru\\\"oz, David Anugraha, En-Shiun Annie Lee, Eric Khiu, Hasti Toossi, Jiaxu Li, Jinyu Liu, Juan Armando Parra Flores, Leandro Acros Roman","submitted_at":"2024-02-04T22:56:56Z","abstract_excerpt":"Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of natural language processing (NLP) tasks using machine learning methods, they primarily focus on high-resource languages, overlooking LRLs and shifts across domains. Focusing on LRLs, we investigate three factors: the size of the fine-tuning corpus, the domain similarity between fine-tuning and testing corpora, and the language similarity between source and target languages. We employ classical regression models to a"},"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":"2402.02633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-04T22:56:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dfceda292e0bae2b539be326c24231fcba1d9b6759e0e2c00f6dc03035fd86a0","abstract_canon_sha256":"76a58c610d7180cb4b2af2b146a1219929e6328fd9ff09c72eb119779420eade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:16.621189Z","signature_b64":"Omt6Kfynk/SCIW92gho+vN8ttKVdScZXi/Rpck14/K09zoNIOuZlJ/sa3O3o/jr9pr+0VE0Y2LObAtcWN6sIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83daf8b98da54b7af71e08c751dd33fe0b0cae1da060e649ae8bd8d4d25eb8d9","last_reissued_at":"2026-07-05T07:41:16.620809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:16.620809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"A. Seza Do\\u{g}ru\\\"oz, David Anugraha, En-Shiun Annie Lee, Eric Khiu, Hasti Toossi, Jiaxu Li, Jinyu Liu, Juan Armando Parra Flores, Leandro Acros Roman","submitted_at":"2024-02-04T22:56:56Z","abstract_excerpt":"Fine-tuning and testing a multilingual large language model is expensive and challenging for low-resource languages (LRLs). While previous studies have predicted the performance of natural language processing (NLP) tasks using machine learning methods, they primarily focus on high-resource languages, overlooking LRLs and shifts across domains. Focusing on LRLs, we investigate three factors: the size of the fine-tuning corpus, the domain similarity between fine-tuning and testing corpora, and the language similarity between source and target languages. We employ classical regression models to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02633","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/2402.02633/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":"2402.02633","created_at":"2026-07-05T07:41:16.620874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02633v1","created_at":"2026-07-05T07:41:16.620874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02633","created_at":"2026-07-05T07:41:16.620874+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPNPROMNUVFX","created_at":"2026-07-05T07:41:16.620874+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPNPROMNUVFXV5Y6","created_at":"2026-07-05T07:41:16.620874+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPNPROMN","created_at":"2026-07-05T07:41:16.620874+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/QPNPROMNUVFXV5Y6BDDVDXJT7Y","json":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y.json","graph_json":"https://pith.science/api/pith-number/QPNPROMNUVFXV5Y6BDDVDXJT7Y/graph.json","events_json":"https://pith.science/api/pith-number/QPNPROMNUVFXV5Y6BDDVDXJT7Y/events.json","paper":"https://pith.science/paper/QPNPROMN"},"agent_actions":{"view_html":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y","download_json":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y.json","view_paper":"https://pith.science/paper/QPNPROMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02633&json=true","fetch_graph":"https://pith.science/api/pith-number/QPNPROMNUVFXV5Y6BDDVDXJT7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/QPNPROMNUVFXV5Y6BDDVDXJT7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y/action/storage_attestation","attest_author":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y/action/author_attestation","sign_citation":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y/action/citation_signature","submit_replication":"https://pith.science/pith/QPNPROMNUVFXV5Y6BDDVDXJT7Y/action/replication_record"}},"created_at":"2026-07-05T07:41:16.620874+00:00","updated_at":"2026-07-05T07:41:16.620874+00:00"}