{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TOJ7LCFRAUHPO3P57MCJTO4VD3","short_pith_number":"pith:TOJ7LCFR","schema_version":"1.0","canonical_sha256":"9b93f588b1050ef76dfdfb0499bb951eed1c5a33b62338399605b9daefbabdc6","source":{"kind":"arxiv","id":"2311.17492","version":2},"attestation_state":"computed","paper":{"title":"Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jean Seo, Minha Kang, Sangah Lee, Sungjoo Byun","submitted_at":"2023-11-29T10:01:48Z","abstract_excerpt":"The Manchu language, with its roots in the historical Manchurian region of Northeast China, is now facing a critical threat of extinction, as there are very few speakers left. In our efforts to safeguard the Manchu language, we introduce Mergen, the first-ever attempt at a Manchu-Korean Machine Translation (MT) model. To develop this model, we utilize valuable resources such as the Manwen Laodang(a historical book) and a Manchu-Korean dictionary. Due to the scarcity of a Manchu-Korean parallel dataset, we expand our data by employing word replacement guided by GloVe embeddings, trained on both"},"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":"2311.17492","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T10:01:48Z","cross_cats_sorted":[],"title_canon_sha256":"12745dc385b3b6c45cb3b6442e18e6d29dae9533945a0346b7e530f2ee713434","abstract_canon_sha256":"f4df5406684ac6e50ae60bfe16099fef67c2e28506303dd4346e3501426c077b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:59.568340Z","signature_b64":"5HtBu6PkgrtEAG4JDEBmzJLDznpcIsC9f+FDCiXkc6PbWuOHXV1tQwvxK4rc6UUCsqbrZEdJLJUojy8+zJLWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b93f588b1050ef76dfdfb0499bb951eed1c5a33b62338399605b9daefbabdc6","last_reissued_at":"2026-07-05T07:32:59.567907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:59.567907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jean Seo, Minha Kang, Sangah Lee, Sungjoo Byun","submitted_at":"2023-11-29T10:01:48Z","abstract_excerpt":"The Manchu language, with its roots in the historical Manchurian region of Northeast China, is now facing a critical threat of extinction, as there are very few speakers left. In our efforts to safeguard the Manchu language, we introduce Mergen, the first-ever attempt at a Manchu-Korean Machine Translation (MT) model. To develop this model, we utilize valuable resources such as the Manwen Laodang(a historical book) and a Manchu-Korean dictionary. Due to the scarcity of a Manchu-Korean parallel dataset, we expand our data by employing word replacement guided by GloVe embeddings, trained on both"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17492","kind":"arxiv","version":2},"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/2311.17492/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":"2311.17492","created_at":"2026-07-05T07:32:59.567964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17492v2","created_at":"2026-07-05T07:32:59.567964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17492","created_at":"2026-07-05T07:32:59.567964+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOJ7LCFRAUHP","created_at":"2026-07-05T07:32:59.567964+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOJ7LCFRAUHPO3P5","created_at":"2026-07-05T07:32:59.567964+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOJ7LCFR","created_at":"2026-07-05T07:32:59.567964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05184","citing_title":"QueEn: A Large Language Model for Quechua-English Translation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3","json":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3.json","graph_json":"https://pith.science/api/pith-number/TOJ7LCFRAUHPO3P57MCJTO4VD3/graph.json","events_json":"https://pith.science/api/pith-number/TOJ7LCFRAUHPO3P57MCJTO4VD3/events.json","paper":"https://pith.science/paper/TOJ7LCFR"},"agent_actions":{"view_html":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3","download_json":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3.json","view_paper":"https://pith.science/paper/TOJ7LCFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17492&json=true","fetch_graph":"https://pith.science/api/pith-number/TOJ7LCFRAUHPO3P57MCJTO4VD3/graph.json","fetch_events":"https://pith.science/api/pith-number/TOJ7LCFRAUHPO3P57MCJTO4VD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3/action/storage_attestation","attest_author":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3/action/author_attestation","sign_citation":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3/action/citation_signature","submit_replication":"https://pith.science/pith/TOJ7LCFRAUHPO3P57MCJTO4VD3/action/replication_record"}},"created_at":"2026-07-05T07:32:59.567964+00:00","updated_at":"2026-07-05T07:32:59.567964+00:00"}