{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SMRPHCYOFF3EZFDQ2PZEXXGKNO","short_pith_number":"pith:SMRPHCYO","schema_version":"1.0","canonical_sha256":"9322f38b0e29764c9470d3f24bdcca6b84a4955e8825f385bb19e69c9ddc7c95","source":{"kind":"arxiv","id":"2505.18683","version":1},"attestation_state":"computed","paper":{"title":"TULUN: Transparent and Adaptable Low-resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Vylomova, Hanna Suominen, Lois Hong, Nick Thieberger, Rapha\\\"el Merx, Trevor Cohn","submitted_at":"2025-05-24T12:58:58Z","abstract_excerpt":"Machine translation (MT) systems that support low-resource languages often struggle on specialized domains. While researchers have proposed various techniques for domain adaptation, these approaches typically require model fine-tuning, making them impractical for non-technical users and small organizations. To address this gap, we propose Tulun, a versatile solution for terminology-aware translation, combining neural MT with large language model (LLM)-based post-editing guided by existing glossaries and translation memories. Our open-source web-based platform enables users to easily create, ed"},"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":"2505.18683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T12:58:58Z","cross_cats_sorted":[],"title_canon_sha256":"0b970bb9024b3be992538cd2baab1d5f96fbd3c3cf5c39fd8428947657801746","abstract_canon_sha256":"b3a612abadd3b8d24027ad5ca648cac0131fadec3ccfe4d0b49a02a356d79687"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:17.816678Z","signature_b64":"r1pANW91BiIX7DRF/4NhZg1ZpFNvLRWZGuCJ5fFOvjwD6k26rSt8nRUXQH2vLBjUmfNKfL6NVyfv5IlHHjb7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9322f38b0e29764c9470d3f24bdcca6b84a4955e8825f385bb19e69c9ddc7c95","last_reissued_at":"2026-07-05T11:09:17.816091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:17.816091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TULUN: Transparent and Adaptable Low-resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Vylomova, Hanna Suominen, Lois Hong, Nick Thieberger, Rapha\\\"el Merx, Trevor Cohn","submitted_at":"2025-05-24T12:58:58Z","abstract_excerpt":"Machine translation (MT) systems that support low-resource languages often struggle on specialized domains. While researchers have proposed various techniques for domain adaptation, these approaches typically require model fine-tuning, making them impractical for non-technical users and small organizations. To address this gap, we propose Tulun, a versatile solution for terminology-aware translation, combining neural MT with large language model (LLM)-based post-editing guided by existing glossaries and translation memories. Our open-source web-based platform enables users to easily create, ed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18683","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/2505.18683/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":"2505.18683","created_at":"2026-07-05T11:09:17.816159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18683v1","created_at":"2026-07-05T11:09:17.816159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18683","created_at":"2026-07-05T11:09:17.816159+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMRPHCYOFF3E","created_at":"2026-07-05T11:09:17.816159+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMRPHCYOFF3EZFDQ","created_at":"2026-07-05T11:09:17.816159+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMRPHCYO","created_at":"2026-07-05T11:09:17.816159+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/SMRPHCYOFF3EZFDQ2PZEXXGKNO","json":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO.json","graph_json":"https://pith.science/api/pith-number/SMRPHCYOFF3EZFDQ2PZEXXGKNO/graph.json","events_json":"https://pith.science/api/pith-number/SMRPHCYOFF3EZFDQ2PZEXXGKNO/events.json","paper":"https://pith.science/paper/SMRPHCYO"},"agent_actions":{"view_html":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO","download_json":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO.json","view_paper":"https://pith.science/paper/SMRPHCYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18683&json=true","fetch_graph":"https://pith.science/api/pith-number/SMRPHCYOFF3EZFDQ2PZEXXGKNO/graph.json","fetch_events":"https://pith.science/api/pith-number/SMRPHCYOFF3EZFDQ2PZEXXGKNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO/action/storage_attestation","attest_author":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO/action/author_attestation","sign_citation":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO/action/citation_signature","submit_replication":"https://pith.science/pith/SMRPHCYOFF3EZFDQ2PZEXXGKNO/action/replication_record"}},"created_at":"2026-07-05T11:09:17.816159+00:00","updated_at":"2026-07-05T11:09:17.816159+00:00"}