{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EGPZE53LL5DEVWWCWLIQM57HFR","short_pith_number":"pith:EGPZE53L","schema_version":"1.0","canonical_sha256":"219f92776b5f464adac2b2d10677e72c4cbd8e47cc668f2ae3ee39f1b55755b3","source":{"kind":"arxiv","id":"2210.05598","version":3},"attestation_state":"computed","paper":{"title":"Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hieu Tran, Lam D. Chau, Long Phan, Minh-Thang Luong, Tai Dang, Trieu H. Trinh, Vy Phan","submitted_at":"2022-10-11T16:35:10Z","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"},"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":"2210.05598","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T16:35:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5972a525b2d6245d39fed3c2154f5a2557dfa584e2f8dcf86f64ca9a331e47c","abstract_canon_sha256":"db4c0e40fa9e89984bd96f8f16104ddf6fdf1e0e4f623b8739473e81dc14cb1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:50.550224Z","signature_b64":"VEf1RgA1EiAy9ED+ukQxtg7pT5wJrPA4zm+BRbthpbD5L/TWS7no0dHBeM8A6NuhJOmUu4MOReLcaXez8PhIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"219f92776b5f464adac2b2d10677e72c4cbd8e47cc668f2ae3ee39f1b55755b3","last_reissued_at":"2026-07-05T05:36:50.549756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:50.549756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hieu Tran, Lam D. Chau, Long Phan, Minh-Thang Luong, Tai Dang, Trieu H. Trinh, Vy Phan","submitted_at":"2022-10-11T16:35:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05598","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/2210.05598/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":"2210.05598","created_at":"2026-07-05T05:36:50.549813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05598v3","created_at":"2026-07-05T05:36:50.549813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05598","created_at":"2026-07-05T05:36:50.549813+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGPZE53LL5DE","created_at":"2026-07-05T05:36:50.549813+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGPZE53LL5DEVWWC","created_at":"2026-07-05T05:36:50.549813+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGPZE53L","created_at":"2026-07-05T05:36:50.549813+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/EGPZE53LL5DEVWWCWLIQM57HFR","json":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR.json","graph_json":"https://pith.science/api/pith-number/EGPZE53LL5DEVWWCWLIQM57HFR/graph.json","events_json":"https://pith.science/api/pith-number/EGPZE53LL5DEVWWCWLIQM57HFR/events.json","paper":"https://pith.science/paper/EGPZE53L"},"agent_actions":{"view_html":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR","download_json":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR.json","view_paper":"https://pith.science/paper/EGPZE53L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05598&json=true","fetch_graph":"https://pith.science/api/pith-number/EGPZE53LL5DEVWWCWLIQM57HFR/graph.json","fetch_events":"https://pith.science/api/pith-number/EGPZE53LL5DEVWWCWLIQM57HFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR/action/storage_attestation","attest_author":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR/action/author_attestation","sign_citation":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR/action/citation_signature","submit_replication":"https://pith.science/pith/EGPZE53LL5DEVWWCWLIQM57HFR/action/replication_record"}},"created_at":"2026-07-05T05:36:50.549813+00:00","updated_at":"2026-07-05T05:36:50.549813+00:00"}