{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CWKTYJDNHVQZ2NVUUG7RBVFI2V","short_pith_number":"pith:CWKTYJDN","schema_version":"1.0","canonical_sha256":"15953c246d3d619d36b4a1bf10d4a8d5409c5719e886b4f18eb20b6d87b2c6f4","source":{"kind":"arxiv","id":"2203.08850","version":3},"attestation_state":"computed","paper":{"title":"Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arya D. McCarthy, David Ifeoluwa Adelani, En-Shiun Annie Lee, Ruisi Su, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga","submitted_at":"2022-03-16T18:15:17Z","abstract_excerpt":"What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages? We conduct a thorough empirical experiment in 10 languages to ascertain this, considering five factors: (1) the amount of fine-tuning data, (2) the noise in the fine-tuning data, (3) the amount of pre-training data in the model, (4) the impact of domain mismatch, and (5) language typology. In addition to yielding several heuristics, the experiments form a framework for evaluating the data sensitivities of machine translation systems. While mBART is robust to domain differe"},"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":"2203.08850","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T18:15:17Z","cross_cats_sorted":[],"title_canon_sha256":"6d3654a3af8465dd0e4442f3474621c7c480ab391d5a47e1ffd3aea171f7bf9d","abstract_canon_sha256":"f5bd83256a71cc4aad73a293301daaae3a6b898d352ce00d9bf65093b306c8d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:07.487798Z","signature_b64":"+AODaHr95HNVKPExtD3uU3a05OaEU9sbQmX4fC/OYxYyMleL9P2tfJRlJA4EEK1AnGo3qKrEGFVRX9E6WKZMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15953c246d3d619d36b4a1bf10d4a8d5409c5719e886b4f18eb20b6d87b2c6f4","last_reissued_at":"2026-07-05T04:19:07.487386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:07.487386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arya D. McCarthy, David Ifeoluwa Adelani, En-Shiun Annie Lee, Ruisi Su, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga","submitted_at":"2022-03-16T18:15:17Z","abstract_excerpt":"What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages? We conduct a thorough empirical experiment in 10 languages to ascertain this, considering five factors: (1) the amount of fine-tuning data, (2) the noise in the fine-tuning data, (3) the amount of pre-training data in the model, (4) the impact of domain mismatch, and (5) language typology. In addition to yielding several heuristics, the experiments form a framework for evaluating the data sensitivities of machine translation systems. While mBART is robust to domain differe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08850","kind":"arxiv","version":3},"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/2203.08850/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":"2203.08850","created_at":"2026-07-05T04:19:07.487447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08850v3","created_at":"2026-07-05T04:19:07.487447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08850","created_at":"2026-07-05T04:19:07.487447+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWKTYJDNHVQZ","created_at":"2026-07-05T04:19:07.487447+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWKTYJDNHVQZ2NVU","created_at":"2026-07-05T04:19:07.487447+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWKTYJDN","created_at":"2026-07-05T04:19:07.487447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V","json":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V.json","graph_json":"https://pith.science/api/pith-number/CWKTYJDNHVQZ2NVUUG7RBVFI2V/graph.json","events_json":"https://pith.science/api/pith-number/CWKTYJDNHVQZ2NVUUG7RBVFI2V/events.json","paper":"https://pith.science/paper/CWKTYJDN"},"agent_actions":{"view_html":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V","download_json":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V.json","view_paper":"https://pith.science/paper/CWKTYJDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08850&json=true","fetch_graph":"https://pith.science/api/pith-number/CWKTYJDNHVQZ2NVUUG7RBVFI2V/graph.json","fetch_events":"https://pith.science/api/pith-number/CWKTYJDNHVQZ2NVUUG7RBVFI2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V/action/storage_attestation","attest_author":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V/action/author_attestation","sign_citation":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V/action/citation_signature","submit_replication":"https://pith.science/pith/CWKTYJDNHVQZ2NVUUG7RBVFI2V/action/replication_record"}},"created_at":"2026-07-05T04:19:07.487447+00:00","updated_at":"2026-07-05T04:19:07.487447+00:00"}