{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZGEKMONW75JXDXMQOPX5L4XC6C","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":"97e2bc2bffec4e776930cd46393454cb8336a4ed440e6070dce8902836c6c2fb","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T02:15:51Z","title_canon_sha256":"2d986db750217f073556e633476152b8e6a0d750db9a783d095d3f5e9099db1c"},"schema_version":"1.0","source":{"id":"2606.24066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24066","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24066v1","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24066","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZGEKMONW75JX","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"ZGEKMONW75JXDXMQ","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"ZGEKMONW","created_at":"2026-06-24T01:14:39Z"}],"graph_snapshots":[{"event_id":"sha256:80c8c04d31e98eef5b5e4d218c35ff75de0f5b5210376291c31f3f82ab9814b4","target":"graph","created_at":"2026-06-24T01:14:39Z","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/2606.24066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bao Thu Ho, Phuong Tuan Dat, Thi Thu Trang Nguyen, Tran Trung Nguyen, Viet Hoang Pham","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T02:15:51Z","title":"VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24066","kind":"arxiv","version":1},"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":"sha256:5260edbc975dad21ec528fcb6d9008077711679a5406fcabbbc99cebff956e36","target":"record","created_at":"2026-06-24T01:14:39Z","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":"97e2bc2bffec4e776930cd46393454cb8336a4ed440e6070dce8902836c6c2fb","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T02:15:51Z","title_canon_sha256":"2d986db750217f073556e633476152b8e6a0d750db9a783d095d3f5e9099db1c"},"schema_version":"1.0","source":{"id":"2606.24066","kind":"arxiv","version":1}},"canonical_sha256":"c988a639b6ff5371dd9073efd5f2e2f088798d7fb68f6c0831cd082a67b9d2bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c988a639b6ff5371dd9073efd5f2e2f088798d7fb68f6c0831cd082a67b9d2bd","first_computed_at":"2026-06-24T01:14:39.473337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:39.473337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eO4JUKbRzXCkowobRSzUchstmdB1NAPY/A78x7OrG0Q8N0Ty4W4JpdWvHfJuFPpfqglVQg35a4HgWHk0QJaSDQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:39.473707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5260edbc975dad21ec528fcb6d9008077711679a5406fcabbbc99cebff956e36","sha256:80c8c04d31e98eef5b5e4d218c35ff75de0f5b5210376291c31f3f82ab9814b4"],"state_sha256":"9848fe19371c6c8bacb364591287b7537f1ec5bc24a16e2f53f6cc04395274c5"}