{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PTKB7E67ONR2BMFXBPTGGRLNRC","short_pith_number":"pith:PTKB7E67","canonical_record":{"source":{"id":"2503.22582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T16:30:28Z","cross_cats_sorted":[],"title_canon_sha256":"c5822a007e35a9e0da503d746637497da99c74c9571003c93f187c0abcda0ab8","abstract_canon_sha256":"f22d425e3f86d288a9927c38aad054b103e610a98e0e2c8adecb489d2f4ef827"},"schema_version":"1.0"},"canonical_sha256":"7cd41f93df7363a0b0b70be663456d88a9a39484bce6d8982e1af291d2153fbd","source":{"kind":"arxiv","id":"2503.22582","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PTKB7E67ONR2BMFXBPTGGRLNRC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.22582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-28T16:30:28Z","cross_cats_sorted":[],"title_canon_sha256":"c5822a007e35a9e0da503d746637497da99c74c9571003c93f187c0abcda0ab8","abstract_canon_sha256":"f22d425e3f86d288a9927c38aad054b103e610a98e0e2c8adecb489d2f4ef827"},"schema_version":"1.0"},"canonical_sha256":"7cd41f93df7363a0b0b70be663456d88a9a39484bce6d8982e1af291d2153fbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:07.076702Z","signature_b64":"fW0oexYx+5Tw50JHpRZbOT8I2AvwBO8ef6j9lSg5nR91nycq1GQuT0K0Hw1n8I++D8gOTQIzLEF0A+kwksZXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd41f93df7363a0b0b70be663456d88a9a39484bce6d8982e1af291d2153fbd","last_reissued_at":"2026-07-05T10:41:07.076130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:07.076130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.22582","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PqfD+bsfxak22fQMiqIjdnHedYa5RZJpHME07z8wsI8GjAXL3LCQ1YQiVDK7x+YH1jXI67hpJNhlh30/D9qyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:42.641492Z"},"content_sha256":"3c8b1e56d4af0f03d2af2967d7a6c4689ec0c8e96eb94fbe9d36f84d1e2b9aaf","schema_version":"1.0","event_id":"sha256:3c8b1e56d4af0f03d2af2967d7a6c4689ec0c8e96eb94fbe9d36f84d1e2b9aaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PTKB7E67ONR2BMFXBPTGGRLNRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"En-Shiun Annie Lee, Sanath Jayasena, Sarubi Thillainathan, Songchen Yuan, Surangika Ranathunga","submitted_at":"2025-03-28T16:30:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22582","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/2503.22582/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbo2YY4pdCpfP4Nf7twGZ0EA2eQ7KlNs2VgBFUwCqMWsZ/+QBc2nMMFGzRQDZcMF52sUf+KFWTKlqvHXHdGFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:42.641982Z"},"content_sha256":"8dff881c8da270e52a7ff148c2c328f1cefe09db318635b61055af5d1d53d72a","schema_version":"1.0","event_id":"sha256:8dff881c8da270e52a7ff148c2c328f1cefe09db318635b61055af5d1d53d72a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTKB7E67ONR2BMFXBPTGGRLNRC/bundle.json","state_url":"https://pith.science/pith/PTKB7E67ONR2BMFXBPTGGRLNRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTKB7E67ONR2BMFXBPTGGRLNRC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T10:49:42Z","links":{"resolver":"https://pith.science/pith/PTKB7E67ONR2BMFXBPTGGRLNRC","bundle":"https://pith.science/pith/PTKB7E67ONR2BMFXBPTGGRLNRC/bundle.json","state":"https://pith.science/pith/PTKB7E67ONR2BMFXBPTGGRLNRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTKB7E67ONR2BMFXBPTGGRLNRC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j48HZNlpqzAQCaUfU7iFm16G1iQ+eZp5gF/mnSmzrqC22G1VQu6sjq/pWFXPaUQUVD67dwV3E2tzLNqx/N5YAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:49:42.645687Z","bundle_sha256":"5e3599853b3ddf9f3a58f9666a601ff376a9807ad1cf58fb232f2d8d97e99ccc"}}