{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CWKTYJDNHVQZ2NVUUG7RBVFI2V","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":"f5bd83256a71cc4aad73a293301daaae3a6b898d352ce00d9bf65093b306c8d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T18:15:17Z","title_canon_sha256":"6d3654a3af8465dd0e4442f3474621c7c480ab391d5a47e1ffd3aea171f7bf9d"},"schema_version":"1.0","source":{"id":"2203.08850","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08850","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08850v3","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08850","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"CWKTYJDNHVQZ","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"CWKTYJDNHVQZ2NVU","created_at":"2026-07-05T04:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"CWKTYJDN","created_at":"2026-07-05T04:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:0b3801f8706e42987f3c61704797fe1796b097334e5f0a29dea6ff2edd2fce30","target":"graph","created_at":"2026-07-05T04:19:07Z","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/2203.08850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arya D. McCarthy, David Ifeoluwa Adelani, En-Shiun Annie Lee, Ruisi Su, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T18:15:17Z","title":"Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08850","kind":"arxiv","version":3},"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":"sha256:4ab115d3b6f1eae44590889e97cb37525d423060c6587fbffc3f54c1b34a0299","target":"record","created_at":"2026-07-05T04:19:07Z","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":"f5bd83256a71cc4aad73a293301daaae3a6b898d352ce00d9bf65093b306c8d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T18:15:17Z","title_canon_sha256":"6d3654a3af8465dd0e4442f3474621c7c480ab391d5a47e1ffd3aea171f7bf9d"},"schema_version":"1.0","source":{"id":"2203.08850","kind":"arxiv","version":3}},"canonical_sha256":"15953c246d3d619d36b4a1bf10d4a8d5409c5719e886b4f18eb20b6d87b2c6f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15953c246d3d619d36b4a1bf10d4a8d5409c5719e886b4f18eb20b6d87b2c6f4","first_computed_at":"2026-07-05T04:19:07.487386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:07.487386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+AODaHr95HNVKPExtD3uU3a05OaEU9sbQmX4fC/OYxYyMleL9P2tfJRlJA4EEK1AnGo3qKrEGFVRX9E6WKZMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:07.487798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08850","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ab115d3b6f1eae44590889e97cb37525d423060c6587fbffc3f54c1b34a0299","sha256:0b3801f8706e42987f3c61704797fe1796b097334e5f0a29dea6ff2edd2fce30"],"state_sha256":"076134954439b7da44951d6421439593dcfc1aca61952b6bd6a54353a0fd7a82"}