{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5UG6KD2ETUQYCL6DKMHBLJERYG","short_pith_number":"pith:5UG6KD2E","schema_version":"1.0","canonical_sha256":"ed0de50f449d21812fc3530e15a491c1bed15b823a818afbbc61d3a17f9be9f9","source":{"kind":"arxiv","id":"2605.18504","version":1},"attestation_state":"computed","paper":{"title":"Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maria Giagkou, Prokopis Prokopidis, Sokratis Sofianopoulos, Spyridon Mavromatis","submitted_at":"2026-05-18T14:56:44Z","abstract_excerpt":"Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parallel data. We address this gap by introducing the AG-MG Parallel Corpus, a new resource containing 132,481 sentence-aligned pairs derived from literary, historical, and biblical texts. We present a novel corpus creation pipeline that combines web-scraped, excerpt-level data with a multi-stage sentence-level alignment, and refinement process. Our method uses VecAlign with LaBSE embeddings, which we first fine-tune on a manually-aligned AG-MG subse"},"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":"2605.18504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T14:56:44Z","cross_cats_sorted":[],"title_canon_sha256":"857652be774a5522dbb38414dd9efe1e940815234b1778f356620b58e2c65ff4","abstract_canon_sha256":"e8f68bf699a164480375b7f69b50be64064af87a20f7fffaa6e3fe91422fb83e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:04.613556Z","signature_b64":"6xbAThW1UVtHl3FRRJQwz+c+U8vjRPAdVTWzP59HbRgVeKzs79R3ayA+dRVTMP9st7GJ8k7pa/GQSU2SKj2NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed0de50f449d21812fc3530e15a491c1bed15b823a818afbbc61d3a17f9be9f9","last_reissued_at":"2026-05-20T00:06:04.612740Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:04.612740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maria Giagkou, Prokopis Prokopidis, Sokratis Sofianopoulos, Spyridon Mavromatis","submitted_at":"2026-05-18T14:56:44Z","abstract_excerpt":"Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parallel data. We address this gap by introducing the AG-MG Parallel Corpus, a new resource containing 132,481 sentence-aligned pairs derived from literary, historical, and biblical texts. We present a novel corpus creation pipeline that combines web-scraped, excerpt-level data with a multi-stage sentence-level alignment, and refinement process. Our method uses VecAlign with LaBSE embeddings, which we first fine-tune on a manually-aligned AG-MG subse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18504","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/2605.18504/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":"2605.18504","created_at":"2026-05-20T00:06:04.612873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18504v1","created_at":"2026-05-20T00:06:04.612873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18504","created_at":"2026-05-20T00:06:04.612873+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UG6KD2ETUQY","created_at":"2026-05-20T00:06:04.612873+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UG6KD2ETUQYCL6D","created_at":"2026-05-20T00:06:04.612873+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UG6KD2E","created_at":"2026-05-20T00:06:04.612873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18504","citing_title":"Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG","json":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG.json","graph_json":"https://pith.science/api/pith-number/5UG6KD2ETUQYCL6DKMHBLJERYG/graph.json","events_json":"https://pith.science/api/pith-number/5UG6KD2ETUQYCL6DKMHBLJERYG/events.json","paper":"https://pith.science/paper/5UG6KD2E"},"agent_actions":{"view_html":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG","download_json":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG.json","view_paper":"https://pith.science/paper/5UG6KD2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18504&json=true","fetch_graph":"https://pith.science/api/pith-number/5UG6KD2ETUQYCL6DKMHBLJERYG/graph.json","fetch_events":"https://pith.science/api/pith-number/5UG6KD2ETUQYCL6DKMHBLJERYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG/action/storage_attestation","attest_author":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG/action/author_attestation","sign_citation":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG/action/citation_signature","submit_replication":"https://pith.science/pith/5UG6KD2ETUQYCL6DKMHBLJERYG/action/replication_record"}},"created_at":"2026-05-20T00:06:04.612873+00:00","updated_at":"2026-05-20T00:06:04.612873+00:00"}