{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QFZJ57A4OXMIKHPWUJ42KOBRLX","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":"25cf489d7b392a966dc8cd06e79b17513c4bfcbbe931993a00e7778c3c5b68cf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:55Z","title_canon_sha256":"fdac84cedb4837da86739032e53b9711690e2cded20fefb77648583d64a5eab1"},"schema_version":"1.0","source":{"id":"2505.21138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21138","created_at":"2026-07-05T11:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21138v2","created_at":"2026-07-05T11:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21138","created_at":"2026-07-05T11:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"QFZJ57A4OXMI","created_at":"2026-07-05T11:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"QFZJ57A4OXMIKHPW","created_at":"2026-07-05T11:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"QFZJ57A4","created_at":"2026-07-05T11:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:8019af5db17c82813d6799425edb504d80f0da5e42cce0df1ad550b8961313de","target":"graph","created_at":"2026-07-05T11:21:47Z","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/2505.21138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in self-supervised learning have shown that self-supervised pre-training, combined with large language models (LLM), can effectively enhance ASR performance in low-resource scenarios. We aim to investigate the effectiveness of this paradigm for Chinese dialects. Specifically, we pre-train a Data2vec2 model on 300,000 hours of unlabeled dialect and accented speech data","authors_text":"Hongjie Chen, Jian Kang, Li Jie, Lv Hang, Tianyi Xu, Wang Qing, Xie Lei, Yongxiang Li, Zhennan Lin","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:55Z","title":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21138","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:b149c8230f0a1a97203b34edec1b88b83fe653624fdcc90e6928c08016b4164d","target":"record","created_at":"2026-07-05T11:21:47Z","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":"25cf489d7b392a966dc8cd06e79b17513c4bfcbbe931993a00e7778c3c5b68cf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:55Z","title_canon_sha256":"fdac84cedb4837da86739032e53b9711690e2cded20fefb77648583d64a5eab1"},"schema_version":"1.0","source":{"id":"2505.21138","kind":"arxiv","version":2}},"canonical_sha256":"81729efc1c75d8851df6a279a538315df20a5a2031658e5b44fcd35c6095c585","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81729efc1c75d8851df6a279a538315df20a5a2031658e5b44fcd35c6095c585","first_computed_at":"2026-07-05T11:21:47.257287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:47.257287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IDM4OIaz59nAPIHc/BASixEWxSVqHXKwET5K/OUI/A35N5kaz4ejxRc6ePB2Kw4Kbrql3SokUXe7MhEd5lkhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:47.257777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b149c8230f0a1a97203b34edec1b88b83fe653624fdcc90e6928c08016b4164d","sha256:8019af5db17c82813d6799425edb504d80f0da5e42cce0df1ad550b8961313de"],"state_sha256":"7d417edbaf8e303f6e372e9ecb597ed463498661a83b3a13a9bb2d0e8d1ab8e1"}