{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CNT73IF2RE5ZJFTFCCKYNRYHBY","short_pith_number":"pith:CNT73IF2","schema_version":"1.0","canonical_sha256":"1367fda0ba893b949665109586c7070e20c74f1ff546601c9074fe92100f46a3","source":{"kind":"arxiv","id":"2412.05862","version":4},"attestation_state":"computed","paper":{"title":"Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Kassahun Wassie, Mahdi Molaei, Yasmin Moslem","submitted_at":"2024-12-08T08:54:13Z","abstract_excerpt":"In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. Our experiments focus on the medical domain and cover four language directions with varied resource availability: English-to-French, English-to-Portuguese, English-to-Swahili, and Swahili-to-English. Despite recent advancements, LLMs demonstrate a significant quality gap in specialized translation compared to multilingual encoder-decoder MT models such as NLLB-200. Our results indicate that NLLB-200 3.3B"},"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":"2412.05862","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-08T08:54:13Z","cross_cats_sorted":[],"title_canon_sha256":"c8e6a82e923f4520bf3e8cc6030ba2633a6db134a8ba72ced51cf164501c0434","abstract_canon_sha256":"4bbb11e79f5b8f1be2cc8edb85b445e75b5bb30048a4f27cdb3620b821a36979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:16.568640Z","signature_b64":"XmLyM2o6CuKBXmND1H0h26q0fd0qZJM6w6t96Xu3TuU3IhiBNBCxHMD8fiCnrGqm/EkdChVZEWb+OGeaJTm8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1367fda0ba893b949665109586c7070e20c74f1ff546601c9074fe92100f46a3","last_reissued_at":"2026-07-05T11:13:16.568108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:16.568108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aman Kassahun Wassie, Mahdi Molaei, Yasmin Moslem","submitted_at":"2024-12-08T08:54:13Z","abstract_excerpt":"In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. Our experiments focus on the medical domain and cover four language directions with varied resource availability: English-to-French, English-to-Portuguese, English-to-Swahili, and Swahili-to-English. Despite recent advancements, LLMs demonstrate a significant quality gap in specialized translation compared to multilingual encoder-decoder MT models such as NLLB-200. Our results indicate that NLLB-200 3.3B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05862","kind":"arxiv","version":4},"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/2412.05862/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":"2412.05862","created_at":"2026-07-05T11:13:16.568169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05862v4","created_at":"2026-07-05T11:13:16.568169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05862","created_at":"2026-07-05T11:13:16.568169+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNT73IF2RE5Z","created_at":"2026-07-05T11:13:16.568169+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNT73IF2RE5ZJFTF","created_at":"2026-07-05T11:13:16.568169+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNT73IF2","created_at":"2026-07-05T11:13:16.568169+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/CNT73IF2RE5ZJFTFCCKYNRYHBY","json":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY.json","graph_json":"https://pith.science/api/pith-number/CNT73IF2RE5ZJFTFCCKYNRYHBY/graph.json","events_json":"https://pith.science/api/pith-number/CNT73IF2RE5ZJFTFCCKYNRYHBY/events.json","paper":"https://pith.science/paper/CNT73IF2"},"agent_actions":{"view_html":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY","download_json":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY.json","view_paper":"https://pith.science/paper/CNT73IF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05862&json=true","fetch_graph":"https://pith.science/api/pith-number/CNT73IF2RE5ZJFTFCCKYNRYHBY/graph.json","fetch_events":"https://pith.science/api/pith-number/CNT73IF2RE5ZJFTFCCKYNRYHBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY/action/storage_attestation","attest_author":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY/action/author_attestation","sign_citation":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY/action/citation_signature","submit_replication":"https://pith.science/pith/CNT73IF2RE5ZJFTFCCKYNRYHBY/action/replication_record"}},"created_at":"2026-07-05T11:13:16.568169+00:00","updated_at":"2026-07-05T11:13:16.568169+00:00"}