{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FWVG5GCFSGLPS6TWYNDVKZP5AF","short_pith_number":"pith:FWVG5GCF","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"},"canonical_sha256":"2daa6e98459196f97a76c3475565fd014cf65e20d85faf3e4b2f00cb08abf2b7","source":{"kind":"arxiv","id":"2602.12911","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12911","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12911v2","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12911","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"FWVG5GCFSGLP","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"FWVG5GCFSGLPS6TW","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"FWVG5GCF","created_at":"2026-06-23T03:14:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FWVG5GCFSGLPS6TWYNDVKZP5AF","target":"record","payload":{"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"},"canonical_sha256":"2daa6e98459196f97a76c3475565fd014cf65e20d85faf3e4b2f00cb08abf2b7","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"},"source_kind":"arxiv","source_id":"2602.12911","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4huSh8itJX16wGEA71bCh9OI/nd9nwBLe4Kqu4f47RoDkswVxs2b3iF6LNdr7OLRyvOkAg0A3Y6Vdr2BuRl5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T21:10:06.551208Z"},"content_sha256":"6815865f06ec71e6654243c38d144cc922b7fc9a33d61a9d441087d0dbd2f89b","schema_version":"1.0","event_id":"sha256:6815865f06ec71e6654243c38d144cc922b7fc9a33d61a9d441087d0dbd2f89b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FWVG5GCFSGLPS6TWYNDVKZP5AF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JczdMZC9/RuUKEN5HEMpIop3InME2qXDvKImpiM+J09/zh6ldqGkHtPyG2gKRPVSlNuV34W/fucWOoVgtFjBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T21:10:06.551606Z"},"content_sha256":"13fd3df6f6e1618088df09a1acde51d01e80f08c96d7731f8116a550d1f2860a","schema_version":"1.0","event_id":"sha256:13fd3df6f6e1618088df09a1acde51d01e80f08c96d7731f8116a550d1f2860a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/bundle.json","state_url":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-03T21:10:06Z","links":{"resolver":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF","bundle":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/bundle.json","state":"https://pith.science/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWVG5GCFSGLPS6TWYNDVKZP5AF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FWVG5GCFSGLPS6TWYNDVKZP5AF","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":"584bf737c64ff6e963e00a028083af3aa872bedb3a31cc3da8930582b01e248e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-13T13:17:16Z","title_canon_sha256":"bce029d01a5e3eee2dc643df6f5ca0bb49da389487ba1cd1c098a24c3afe5345"},"schema_version":"1.0","source":{"id":"2602.12911","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12911","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12911v2","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12911","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"FWVG5GCFSGLP","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"FWVG5GCFSGLPS6TW","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"FWVG5GCF","created_at":"2026-06-23T03:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:13fd3df6f6e1618088df09a1acde51d01e80f08c96d7731f8116a550d1f2860a","target":"graph","created_at":"2026-06-23T03:14:28Z","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/2602.12911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-13T13:17:16Z","title":"ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12911","kind":"arxiv","version":2},"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":"sha256:6815865f06ec71e6654243c38d144cc922b7fc9a33d61a9d441087d0dbd2f89b","target":"record","created_at":"2026-06-23T03:14:28Z","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":"584bf737c64ff6e963e00a028083af3aa872bedb3a31cc3da8930582b01e248e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-13T13:17:16Z","title_canon_sha256":"bce029d01a5e3eee2dc643df6f5ca0bb49da389487ba1cd1c098a24c3afe5345"},"schema_version":"1.0","source":{"id":"2602.12911","kind":"arxiv","version":2}},"canonical_sha256":"2daa6e98459196f97a76c3475565fd014cf65e20d85faf3e4b2f00cb08abf2b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2daa6e98459196f97a76c3475565fd014cf65e20d85faf3e4b2f00cb08abf2b7","first_computed_at":"2026-06-23T03:14:28.457656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:28.457656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M0sMuqZp6BFZdV/m8+5wEr5zT6oHpRNCy9H8l8485AQFRo9jBXHYuLFL5TKxTFXDGHzi+KSBKJ8Mdk1EWbAWDA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:28.458144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.12911","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6815865f06ec71e6654243c38d144cc922b7fc9a33d61a9d441087d0dbd2f89b","sha256:13fd3df6f6e1618088df09a1acde51d01e80f08c96d7731f8116a550d1f2860a"],"state_sha256":"ff15d5314cd0dcb19f1ffe1d1722cfc4cd811bb5f7c9b114f7c03392d18f89a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jnW4Qs5hjICT/TEY55WggYPU0r0dAvDy8nHNsQ8Oict5JmHXkjfvze7knK5Hemo+eWVE6+9zr+QbbFBbAmtICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T21:10:06.553595Z","bundle_sha256":"76dbfcc84202afb5763cfb5f7f4db0fd2f69b60552ad92034e143ed56d19d6d6"}}