{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2NNTZQQRCRPO7CYRQSRKHTPTQP","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":"975823ad300f259d72fe291577af0d47414719b83bc59e57dc23db6f1ea1c82b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:21:40Z","title_canon_sha256":"92e085de9d63e8109f9a31ff38b86e35ec9da6f06fa1fafdb9b8dc4416d6f90d"},"schema_version":"1.0","source":{"id":"2606.10360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10360","created_at":"2026-06-10T01:10:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10360v1","created_at":"2026-06-10T01:10:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10360","created_at":"2026-06-10T01:10:13Z"},{"alias_kind":"pith_short_12","alias_value":"2NNTZQQRCRPO","created_at":"2026-06-10T01:10:13Z"},{"alias_kind":"pith_short_16","alias_value":"2NNTZQQRCRPO7CYR","created_at":"2026-06-10T01:10:13Z"},{"alias_kind":"pith_short_8","alias_value":"2NNTZQQR","created_at":"2026-06-10T01:10:13Z"}],"graph_snapshots":[{"event_id":"sha256:260ece81ddfff5b6b58197e9042b2073bcbde56ac0047bb6457d199ebb93f7c4","target":"graph","created_at":"2026-06-10T01:10:13Z","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/2606.10360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ViP-VL, an efficient Vietnamese Self-supervised speech Pretraining model leveraging Vector-quantization Learning. To bridge the gap between high-resolution audio and efficient processing, ViP-VL incorporates Acoustic Stacking and Receptive Field Alignment to enable a synchronized 8x subsampling rate within the ChunkFormer architecture, while further enhancing representation robustness through a specialized Mask Selection Strategy during pretraining on the BEST-RQ framework. Pretrained on 17,000 hours of unlabeled Vietnamese speech, our model establishes new state-of-the-art results ","authors_text":"Bao Nguyen, Dung Vo, Duy Vo, Khanh Le, Khoa D Doan, Kiet Anh Hoang, Linh Pham, Thai Tran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:21:40Z","title":"ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10360","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:b6b0e0b9a2ef23edf9953dfd9ff747f0e5d2386fbcf635763010621434b56088","target":"record","created_at":"2026-06-10T01:10:13Z","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":"975823ad300f259d72fe291577af0d47414719b83bc59e57dc23db6f1ea1c82b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T03:21:40Z","title_canon_sha256":"92e085de9d63e8109f9a31ff38b86e35ec9da6f06fa1fafdb9b8dc4416d6f90d"},"schema_version":"1.0","source":{"id":"2606.10360","kind":"arxiv","version":1}},"canonical_sha256":"d35b3cc211145eef8b1184a2a3cdf383e2b55c358a0c65f8a3f961450700e2f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d35b3cc211145eef8b1184a2a3cdf383e2b55c358a0c65f8a3f961450700e2f5","first_computed_at":"2026-06-10T01:10:13.655671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:13.655671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"879T+RPiPRUqN35bV0uzv9Ah2pOJobJbrDOAfCBuBpJNROPlDOxgmvQi57KtAONJQZITPYCYlNRA6CqoxQLfAg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:13.656615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6b0e0b9a2ef23edf9953dfd9ff747f0e5d2386fbcf635763010621434b56088","sha256:260ece81ddfff5b6b58197e9042b2073bcbde56ac0047bb6457d199ebb93f7c4"],"state_sha256":"0c445b53197f3785132cd17eb795695fab2b1fe5e500035b4964e5de08aa5b27"}