{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DD35RNZ6KCJ7Z3A7COIFJCRC2P","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":"17e72ac7f53b32ab7e3b15a243191565d3d259cfc812fe541d4d95dc58e05d54","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T09:48:11Z","title_canon_sha256":"bf6725e4b3916122778264c51c694a6881b8ff882002b9decdae3d90f6d69192"},"schema_version":"1.0","source":{"id":"2409.08680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08680","created_at":"2026-07-05T09:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08680v1","created_at":"2026-07-05T09:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08680","created_at":"2026-07-05T09:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"DD35RNZ6KCJ7","created_at":"2026-07-05T09:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"DD35RNZ6KCJ7Z3A7","created_at":"2026-07-05T09:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"DD35RNZ6","created_at":"2026-07-05T09:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:21ea42b93f33158560a4d8048b2640080b30208387c04a5168ec10a674c0acf0","target":"graph","created_at":"2026-07-05T09:06:45Z","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/2409.08680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with bidirectional context, and lack sufficient support for downstream streaming models. To address this issue, we introduce the next token prediction based speech pre-training method with random-projection quantizer (NEST-RQ). NEST-RQ employs causal encoders with only left context and uses next token prediction (NTP) as the training task. On the large-scale datase","authors_text":"Chen Shen, Linhao Dong, Lu Lu, Mingkun Huang, Minglun Han, Ye Bai, Youjia Huang, Yuxuan Wang, Zehua Lin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T09:48:11Z","title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08680","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":"sha256:34dca9bc3d7d4d59dda73394cc2c5fe1434e854463b1ac7e618e6c2f6484420a","target":"record","created_at":"2026-07-05T09:06:45Z","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":"17e72ac7f53b32ab7e3b15a243191565d3d259cfc812fe541d4d95dc58e05d54","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T09:48:11Z","title_canon_sha256":"bf6725e4b3916122778264c51c694a6881b8ff882002b9decdae3d90f6d69192"},"schema_version":"1.0","source":{"id":"2409.08680","kind":"arxiv","version":1}},"canonical_sha256":"18f7d8b73e5093fcec1f1390548a22d3c9bf9a3259f447b0676681c88f1576d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18f7d8b73e5093fcec1f1390548a22d3c9bf9a3259f447b0676681c88f1576d6","first_computed_at":"2026-07-05T09:06:45.719649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:45.719649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ero5c9l+cT9MnqjLVq2mnwrGJPyKxzgRzI6qYFUblL2PK+T3iGTuW9+w5fPFhdOsYINAr3HKzx8H9ERSLXaOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:45.720135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34dca9bc3d7d4d59dda73394cc2c5fe1434e854463b1ac7e618e6c2f6484420a","sha256:21ea42b93f33158560a4d8048b2640080b30208387c04a5168ec10a674c0acf0"],"state_sha256":"069194168373df547601c81becf447b78618f97d7662a5c4274c66bf209e4af2"}