{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FWVG5GCFSGLPS6TWYNDVKZP5AF","short_pith_number":"pith:FWVG5GCF","schema_version":"1.0","canonical_sha256":"2daa6e98459196f97a76c3475565fd014cf65e20d85faf3e4b2f00cb08abf2b7","source":{"kind":"arxiv","id":"2602.12911","version":2},"attestation_state":"computed","paper":{"title":"ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chien Dinh Huynh, Dung D. Le, Duy Mai Hoang, Giang-Son Nguyen, Inigo Jauregi Unanue, Massimo Piccardi, Nhu Vo, Tung X. Nguyen, Wray Buntine","submitted_at":"2026-02-13T13:17:16Z","abstract_excerpt":"Code-switching (CS), which is when Vietnamese speech uses English words like drug names or procedures, is a common phenomenon in Vietnamese medical communication. This creates challenges for Automatic Speech Recognition (ASR) systems, especially in low-resource languages like Vietnamese. Current most ASR systems struggle to recognize correctly English medical terms within Vietnamese sentences, and no benchmark addresses this challenge. In this paper, we construct a 34-hour Vietnamese Medical Code-Switching Speech dataset (ViMedCSS) containing 16,576 utterances. Each utterance includes at least"},"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":"2602.12911","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-13T13:17:16Z","cross_cats_sorted":[],"title_canon_sha256":"bce029d01a5e3eee2dc643df6f5ca0bb49da389487ba1cd1c098a24c3afe5345","abstract_canon_sha256":"584bf737c64ff6e963e00a028083af3aa872bedb3a31cc3da8930582b01e248e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:28.458144Z","signature_b64":"M0sMuqZp6BFZdV/m8+5wEr5zT6oHpRNCy9H8l8485AQFRo9jBXHYuLFL5TKxTFXDGHzi+KSBKJ8Mdk1EWbAWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2daa6e98459196f97a76c3475565fd014cf65e20d85faf3e4b2f00cb08abf2b7","last_reissued_at":"2026-06-23T03:14:28.457656Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:28.457656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chien Dinh Huynh, Dung D. Le, Duy Mai Hoang, Giang-Son Nguyen, Inigo Jauregi Unanue, Massimo Piccardi, Nhu Vo, Tung X. Nguyen, Wray Buntine","submitted_at":"2026-02-13T13:17:16Z","abstract_excerpt":"Code-switching (CS), which is when Vietnamese speech uses English words like drug names or procedures, is a common phenomenon in Vietnamese medical communication. This creates challenges for Automatic Speech Recognition (ASR) systems, especially in low-resource languages like Vietnamese. Current most ASR systems struggle to recognize correctly English medical terms within Vietnamese sentences, and no benchmark addresses this challenge. In this paper, we construct a 34-hour Vietnamese Medical Code-Switching Speech dataset (ViMedCSS) containing 16,576 utterances. Each utterance includes at least"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12911","kind":"arxiv","version":2},"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/2602.12911/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":"2602.12911","created_at":"2026-06-23T03:14:28.457715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12911v2","created_at":"2026-06-23T03:14:28.457715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12911","created_at":"2026-06-23T03:14:28.457715+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWVG5GCFSGLP","created_at":"2026-06-23T03:14:28.457715+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWVG5GCFSGLPS6TW","created_at":"2026-06-23T03:14:28.457715+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWVG5GCF","created_at":"2026-06-23T03:14:28.457715+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/FWVG5GCFSGLPS6TWYNDVKZP5AF","json":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF.json","graph_json":"https://pith.science/api/pith-number/FWVG5GCFSGLPS6TWYNDVKZP5AF/graph.json","events_json":"https://pith.science/api/pith-number/FWVG5GCFSGLPS6TWYNDVKZP5AF/events.json","paper":"https://pith.science/paper/FWVG5GCF"},"agent_actions":{"view_html":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF","download_json":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF.json","view_paper":"https://pith.science/paper/FWVG5GCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12911&json=true","fetch_graph":"https://pith.science/api/pith-number/FWVG5GCFSGLPS6TWYNDVKZP5AF/graph.json","fetch_events":"https://pith.science/api/pith-number/FWVG5GCFSGLPS6TWYNDVKZP5AF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/action/storage_attestation","attest_author":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/action/author_attestation","sign_citation":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/action/citation_signature","submit_replication":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/action/replication_record"}},"created_at":"2026-06-23T03:14:28.457715+00:00","updated_at":"2026-06-23T03:14:28.457715+00:00"}