{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7U5KGY5V2XDQLBCM6MZ7II3MYQ","short_pith_number":"pith:7U5KGY5V","schema_version":"1.0","canonical_sha256":"fd3aa363b5d5c705844cf333f4236cc41817f062abecb48dd9d36c35a6169869","source":{"kind":"arxiv","id":"2508.10683","version":1},"attestation_state":"computed","paper":{"title":"Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nasma Chaoui, Richard Khoury","submitted_at":"2025-08-14T14:25:34Z","abstract_excerpt":"This paper presents the first systematic study of strategies for translating Coptic into French. Our comprehensive pipeline systematically evaluates: pivot versus direct translation, the impact of pre-training, the benefits of multi-version fine-tuning, and model robustness to noise. Utilizing aligned biblical corpora, we demonstrate that fine-tuning with a stylistically-varied and noise-aware training corpus significantly enhances translation quality. Our findings provide crucial practical insights for developing translation tools for historical languages in general."},"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":"2508.10683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T14:25:34Z","cross_cats_sorted":[],"title_canon_sha256":"ee08b4b4e1b0244770ea5bf956586046baafb349a1fb4e0b4a9aac7850ec8ce1","abstract_canon_sha256":"4ed108b20b8a8f2a8036607b50386da468fd39486c09636c332633f2e81ab45a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:12.414444Z","signature_b64":"6gbPvmQWA0hyReL6xm5P3Tty6jauGij+bvZMkGqY9Ytkn2FhFGWOIXdiQbJf2egju+u+wrHFfbkuCFVJvQosBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd3aa363b5d5c705844cf333f4236cc41817f062abecb48dd9d36c35a6169869","last_reissued_at":"2026-05-18T03:10:12.413881Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:12.413881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nasma Chaoui, Richard Khoury","submitted_at":"2025-08-14T14:25:34Z","abstract_excerpt":"This paper presents the first systematic study of strategies for translating Coptic into French. Our comprehensive pipeline systematically evaluates: pivot versus direct translation, the impact of pre-training, the benefits of multi-version fine-tuning, and model robustness to noise. Utilizing aligned biblical corpora, we demonstrate that fine-tuning with a stylistically-varied and noise-aware training corpus significantly enhances translation quality. Our findings provide crucial practical insights for developing translation tools for historical languages in general."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10683","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":""},"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":"2508.10683","created_at":"2026-05-18T03:10:12.413971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10683v1","created_at":"2026-05-18T03:10:12.413971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10683","created_at":"2026-05-18T03:10:12.413971+00:00"},{"alias_kind":"pith_short_12","alias_value":"7U5KGY5V2XDQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7U5KGY5V2XDQLBCM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7U5KGY5V","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18758","citing_title":"Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ","json":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ.json","graph_json":"https://pith.science/api/pith-number/7U5KGY5V2XDQLBCM6MZ7II3MYQ/graph.json","events_json":"https://pith.science/api/pith-number/7U5KGY5V2XDQLBCM6MZ7II3MYQ/events.json","paper":"https://pith.science/paper/7U5KGY5V"},"agent_actions":{"view_html":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ","download_json":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ.json","view_paper":"https://pith.science/paper/7U5KGY5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10683&json=true","fetch_graph":"https://pith.science/api/pith-number/7U5KGY5V2XDQLBCM6MZ7II3MYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7U5KGY5V2XDQLBCM6MZ7II3MYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ/action/storage_attestation","attest_author":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ/action/author_attestation","sign_citation":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ/action/citation_signature","submit_replication":"https://pith.science/pith/7U5KGY5V2XDQLBCM6MZ7II3MYQ/action/replication_record"}},"created_at":"2026-05-18T03:10:12.413971+00:00","updated_at":"2026-05-18T03:10:12.413971+00:00"}