{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q2LZZAW7PQWTRW5RJ5RHVJTL5X","short_pith_number":"pith:Q2LZZAW7","schema_version":"1.0","canonical_sha256":"86979c82df7c2d38dbb14f627aa66bedda9a82c655fb01485c4380c848b0199b","source":{"kind":"arxiv","id":"2104.03879","version":1},"attestation_state":"computed","paper":{"title":"COVID-19 Named Entity Recognition for Vietnamese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dat Quoc Nguyen, Mai Hoang Dao, Thinh Hung Truong","submitted_at":"2021-04-08T16:35:34Z","abstract_excerpt":"The current COVID-19 pandemic has lead to the creation of many corpora that facilitate NLP research and downstream applications to help fight the pandemic. However, most of these corpora are exclusively for English. As the pandemic is a global problem, it is worth creating COVID-19 related datasets for languages other than English. In this paper, we present the first manually-annotated COVID-19 domain-specific dataset for Vietnamese. Particularly, our dataset is annotated for the named entity recognition (NER) task with newly-defined entity types that can be used in other future epidemics. Our"},"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":"2104.03879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T16:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"4a8c141aaf7d9c47e28cca246213cc998d28c81c9d889284416e8efca981f42c","abstract_canon_sha256":"da27202d7eb48ad76cadceab5477ef5170701f5d1de24a542e88a0be26805d9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:24.560468Z","signature_b64":"QZCpDY81yabsqfYvzTfvTsC0HxS/hiK2pBTI3mDRseylkUNeJBPgcOhNZBkChoPIeClBTMDkM1cGk2q2TTrQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86979c82df7c2d38dbb14f627aa66bedda9a82c655fb01485c4380c848b0199b","last_reissued_at":"2026-07-05T02:30:24.559956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:24.559956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COVID-19 Named Entity Recognition for Vietnamese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dat Quoc Nguyen, Mai Hoang Dao, Thinh Hung Truong","submitted_at":"2021-04-08T16:35:34Z","abstract_excerpt":"The current COVID-19 pandemic has lead to the creation of many corpora that facilitate NLP research and downstream applications to help fight the pandemic. However, most of these corpora are exclusively for English. As the pandemic is a global problem, it is worth creating COVID-19 related datasets for languages other than English. In this paper, we present the first manually-annotated COVID-19 domain-specific dataset for Vietnamese. Particularly, our dataset is annotated for the named entity recognition (NER) task with newly-defined entity types that can be used in other future epidemics. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03879","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/2104.03879/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":"2104.03879","created_at":"2026-07-05T02:30:24.560015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03879v1","created_at":"2026-07-05T02:30:24.560015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03879","created_at":"2026-07-05T02:30:24.560015+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2LZZAW7PQWT","created_at":"2026-07-05T02:30:24.560015+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2LZZAW7PQWTRW5R","created_at":"2026-07-05T02:30:24.560015+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2LZZAW7","created_at":"2026-07-05T02:30:24.560015+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/Q2LZZAW7PQWTRW5RJ5RHVJTL5X","json":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X.json","graph_json":"https://pith.science/api/pith-number/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/graph.json","events_json":"https://pith.science/api/pith-number/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/events.json","paper":"https://pith.science/paper/Q2LZZAW7"},"agent_actions":{"view_html":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X","download_json":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X.json","view_paper":"https://pith.science/paper/Q2LZZAW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03879&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/action/storage_attestation","attest_author":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/action/author_attestation","sign_citation":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/action/citation_signature","submit_replication":"https://pith.science/pith/Q2LZZAW7PQWTRW5RJ5RHVJTL5X/action/replication_record"}},"created_at":"2026-07-05T02:30:24.560015+00:00","updated_at":"2026-07-05T02:30:24.560015+00:00"}