{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZGEKMONW75JXDXMQOPX5L4XC6C","short_pith_number":"pith:ZGEKMONW","schema_version":"1.0","canonical_sha256":"c988a639b6ff5371dd9073efd5f2e2f088798d7fb68f6c0831cd082a67b9d2bd","source":{"kind":"arxiv","id":"2606.24066","version":1},"attestation_state":"computed","paper":{"title":"VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bao Thu Ho, Phuong Tuan Dat, Thi Thu Trang Nguyen, Tran Trung Nguyen, Viet Hoang Pham","submitted_at":"2026-06-23T02:15:51Z","abstract_excerpt":"Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity. Most large-scale datasets rely on facial cues to link speech with speaker identities, restricting data collection to recordings where speakers appear on camera. We propose a face-independent dataset construction pipeline and introduce VieSpeaker, a large-scale Vietnamese speaker recognition dataset. Our approach leverages textual metadata and large language model reasoning to infer speaker identities from transcripts"},"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":"2606.24066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T02:15:51Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"2d986db750217f073556e633476152b8e6a0d750db9a783d095d3f5e9099db1c","abstract_canon_sha256":"97e2bc2bffec4e776930cd46393454cb8336a4ed440e6070dce8902836c6c2fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:39.473707Z","signature_b64":"eO4JUKbRzXCkowobRSzUchstmdB1NAPY/A78x7OrG0Q8N0Ty4W4JpdWvHfJuFPpfqglVQg35a4HgWHk0QJaSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c988a639b6ff5371dd9073efd5f2e2f088798d7fb68f6c0831cd082a67b9d2bd","last_reissued_at":"2026-06-24T01:14:39.473337Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:39.473337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bao Thu Ho, Phuong Tuan Dat, Thi Thu Trang Nguyen, Tran Trung Nguyen, Viet Hoang Pham","submitted_at":"2026-06-23T02:15:51Z","abstract_excerpt":"Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity. Most large-scale datasets rely on facial cues to link speech with speaker identities, restricting data collection to recordings where speakers appear on camera. We propose a face-independent dataset construction pipeline and introduce VieSpeaker, a large-scale Vietnamese speaker recognition dataset. Our approach leverages textual metadata and large language model reasoning to infer speaker identities from transcripts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24066","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/2606.24066/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":"2606.24066","created_at":"2026-06-24T01:14:39.473398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24066v1","created_at":"2026-06-24T01:14:39.473398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24066","created_at":"2026-06-24T01:14:39.473398+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGEKMONW75JX","created_at":"2026-06-24T01:14:39.473398+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGEKMONW75JXDXMQ","created_at":"2026-06-24T01:14:39.473398+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGEKMONW","created_at":"2026-06-24T01:14:39.473398+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/ZGEKMONW75JXDXMQOPX5L4XC6C","json":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C.json","graph_json":"https://pith.science/api/pith-number/ZGEKMONW75JXDXMQOPX5L4XC6C/graph.json","events_json":"https://pith.science/api/pith-number/ZGEKMONW75JXDXMQOPX5L4XC6C/events.json","paper":"https://pith.science/paper/ZGEKMONW"},"agent_actions":{"view_html":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C","download_json":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C.json","view_paper":"https://pith.science/paper/ZGEKMONW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24066&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGEKMONW75JXDXMQOPX5L4XC6C/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGEKMONW75JXDXMQOPX5L4XC6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C/action/storage_attestation","attest_author":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C/action/author_attestation","sign_citation":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C/action/citation_signature","submit_replication":"https://pith.science/pith/ZGEKMONW75JXDXMQOPX5L4XC6C/action/replication_record"}},"created_at":"2026-06-24T01:14:39.473398+00:00","updated_at":"2026-06-24T01:14:39.473398+00:00"}