{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BIIMAKK7HS7TE2FPCEIVKDCTNC","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":"98b93e0c02350581f8478374d8aa64a3dd57fcff261f8273c0547a35ef56fbf9","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:57:12Z","title_canon_sha256":"66164603b757c77e610e44124051ecb737f17fd632acc80f32cd77e556aca925"},"schema_version":"1.0","source":{"id":"2504.04060","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04060","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04060v2","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04060","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"BIIMAKK7HS7T","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"BIIMAKK7HS7TE2FP","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"BIIMAKK7","created_at":"2026-07-05T10:52:21Z"}],"graph_snapshots":[{"event_id":"sha256:ef38abb540ba86acbeb3752c7e6c32c0f6c083f0b0d17809c5fe8fd5244272d4","target":"graph","created_at":"2026-07-05T10:52:21Z","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/2504.04060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. We introduce VocalNet-1B and VocalNet-8B, a series of high-performance, low-latency speech LLMs enabled by a scalable and model-agnostic training framework designed for real-time voice interaction. Central to our contribution is the first application of multi-token prediction (MTP) to speech LLMs. This approach represents a paradigm shift from standard next-token prediction (NTP), offering simultaneous improvements in generation speed and quality. Informed by analysis of MTP's effect on speech ","authors_text":"Heyang Liu, Qunshan Gu, Ronghua Wu, Yanfeng Wang, Yuhao Wang, Yu Wang, Ziyang Cheng","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:57:12Z","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04060","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":"sha256:510d4ae0e0988437a398f5d583daf9ec97d7cb003e9f1c8437ab48a3ab66a5cd","target":"record","created_at":"2026-07-05T10:52:21Z","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":"98b93e0c02350581f8478374d8aa64a3dd57fcff261f8273c0547a35ef56fbf9","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:57:12Z","title_canon_sha256":"66164603b757c77e610e44124051ecb737f17fd632acc80f32cd77e556aca925"},"schema_version":"1.0","source":{"id":"2504.04060","kind":"arxiv","version":2}},"canonical_sha256":"0a10c0295f3cbf3268af1111550c5368a02f4f4040323ee5c0cc1b0c06f46799","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a10c0295f3cbf3268af1111550c5368a02f4f4040323ee5c0cc1b0c06f46799","first_computed_at":"2026-07-05T10:52:21.770413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:21.770413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iKY/Ta/nPslFRg7Z+KI/GBvoPFHlgWggthrc/7PhT0Izt/9Q9ebN9/MzAqUPQE/aSLJEU6oIEcOkN8cYiHQmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:21.770882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04060","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:510d4ae0e0988437a398f5d583daf9ec97d7cb003e9f1c8437ab48a3ab66a5cd","sha256:ef38abb540ba86acbeb3752c7e6c32c0f6c083f0b0d17809c5fe8fd5244272d4"],"state_sha256":"30f8aa86ba2b92cc04396c99f6a99535b7ad79d52a243ed6a119a8e2671f9d1a"}