{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PTKB7E67ONR2BMFXBPTGGRLNRC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f22d425e3f86d288a9927c38aad054b103e610a98e0e2c8adecb489d2f4ef827","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T16:30:28Z","title_canon_sha256":"c5822a007e35a9e0da503d746637497da99c74c9571003c93f187c0abcda0ab8"},"schema_version":"1.0","source":{"id":"2503.22582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22582","created_at":"2026-07-05T10:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22582v1","created_at":"2026-07-05T10:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22582","created_at":"2026-07-05T10:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"PTKB7E67ONR2","created_at":"2026-07-05T10:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"PTKB7E67ONR2BMFX","created_at":"2026-07-05T10:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"PTKB7E67","created_at":"2026-07-05T10:41:07Z"}],"graph_snapshots":[{"event_id":"sha256:8dff881c8da270e52a7ff148c2c328f1cefe09db318635b61055af5d1d53d72a","target":"graph","created_at":"2026-07-05T10:41:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.22582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning multilingual sequence-to-sequence large language models (msLLMs) has shown promise in developing neural machine translation (NMT) systems for low-resource languages (LRLs). However, conventional single-stage fine-tuning methods struggle in extremely low-resource NMT settings, where training data is very limited. This paper contributes to artificial intelligence by proposing two approaches for adapting msLLMs in these challenging scenarios: (1) continual pre-training (CPT), where the msLLM is further trained with domain-specific monolingual data to compensate for the under-represent","authors_text":"En-Shiun Annie Lee, Sanath Jayasena, Sarubi Thillainathan, Songchen Yuan, Surangika Ranathunga","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T16:30:28Z","title":"Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22582","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3c8b1e56d4af0f03d2af2967d7a6c4689ec0c8e96eb94fbe9d36f84d1e2b9aaf","target":"record","created_at":"2026-07-05T10:41:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f22d425e3f86d288a9927c38aad054b103e610a98e0e2c8adecb489d2f4ef827","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T16:30:28Z","title_canon_sha256":"c5822a007e35a9e0da503d746637497da99c74c9571003c93f187c0abcda0ab8"},"schema_version":"1.0","source":{"id":"2503.22582","kind":"arxiv","version":1}},"canonical_sha256":"7cd41f93df7363a0b0b70be663456d88a9a39484bce6d8982e1af291d2153fbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cd41f93df7363a0b0b70be663456d88a9a39484bce6d8982e1af291d2153fbd","first_computed_at":"2026-07-05T10:41:07.076130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:07.076130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fW0oexYx+5Tw50JHpRZbOT8I2AvwBO8ef6j9lSg5nR91nycq1GQuT0K0Hw1n8I++D8gOTQIzLEF0A+kwksZXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:07.076702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c8b1e56d4af0f03d2af2967d7a6c4689ec0c8e96eb94fbe9d36f84d1e2b9aaf","sha256:8dff881c8da270e52a7ff148c2c328f1cefe09db318635b61055af5d1d53d72a"],"state_sha256":"d1c2e2b489d05efac4737df546053ed69e8eab50014177ab4a57a3a981f8d31a"}