{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EGPZE53LL5DEVWWCWLIQM57HFR","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":"db4c0e40fa9e89984bd96f8f16104ddf6fdf1e0e4f623b8739473e81dc14cb1d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T16:35:10Z","title_canon_sha256":"b5972a525b2d6245d39fed3c2154f5a2557dfa584e2f8dcf86f64ca9a331e47c"},"schema_version":"1.0","source":{"id":"2210.05598","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05598","created_at":"2026-07-05T05:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05598v3","created_at":"2026-07-05T05:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05598","created_at":"2026-07-05T05:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"EGPZE53LL5DE","created_at":"2026-07-05T05:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"EGPZE53LL5DEVWWC","created_at":"2026-07-05T05:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"EGPZE53L","created_at":"2026-07-05T05:36:50Z"}],"graph_snapshots":[{"event_id":"sha256:50e70b0b978890f7b3ed4ffe814bd8c17101178a272cb357d53918ade76bbc96","target":"graph","created_at":"2026-07-05T05:36:50Z","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/2210.05598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Biomedical data and benchmarks are highly valuable yet very limited in low-resource languages other than English such as Vietnamese. In this paper, we make use of a state-of-the-art translation model in English-Vietnamese to translate and produce both pretrained as well as supervised data in the biomedical domains. Thanks to such large-scale translation, we introduce ViPubmedT5, a pretrained Encoder-Decoder Transformer model trained on 20 million translated abstracts from the high-quality public PubMed corpus. ViPubMedT5 demonstrates state-of-the-art results on two different biomedical benchma","authors_text":"Hieu Tran, Lam D. Chau, Long Phan, Minh-Thang Luong, Tai Dang, Trieu H. Trinh, Vy Phan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T16:35:10Z","title":"Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05598","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:cd917b472616d8be8712b57c1f15897236e81812b9fefd9ecb13990d28d11568","target":"record","created_at":"2026-07-05T05:36:50Z","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":"db4c0e40fa9e89984bd96f8f16104ddf6fdf1e0e4f623b8739473e81dc14cb1d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T16:35:10Z","title_canon_sha256":"b5972a525b2d6245d39fed3c2154f5a2557dfa584e2f8dcf86f64ca9a331e47c"},"schema_version":"1.0","source":{"id":"2210.05598","kind":"arxiv","version":3}},"canonical_sha256":"219f92776b5f464adac2b2d10677e72c4cbd8e47cc668f2ae3ee39f1b55755b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"219f92776b5f464adac2b2d10677e72c4cbd8e47cc668f2ae3ee39f1b55755b3","first_computed_at":"2026-07-05T05:36:50.549756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:50.549756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VEf1RgA1EiAy9ED+ukQxtg7pT5wJrPA4zm+BRbthpbD5L/TWS7no0dHBeM8A6NuhJOmUu4MOReLcaXez8PhIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:50.550224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05598","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd917b472616d8be8712b57c1f15897236e81812b9fefd9ecb13990d28d11568","sha256:50e70b0b978890f7b3ed4ffe814bd8c17101178a272cb357d53918ade76bbc96"],"state_sha256":"7f9739157ef6ad099d38f44dc6f3a43cecaef595e75a5d3d4a929809ec69e1cf"}