{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BIIMAKK7HS7TE2FPCEIVKDCTNC","short_pith_number":"pith:BIIMAKK7","canonical_record":{"source":{"id":"2504.04060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:57:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"66164603b757c77e610e44124051ecb737f17fd632acc80f32cd77e556aca925","abstract_canon_sha256":"98b93e0c02350581f8478374d8aa64a3dd57fcff261f8273c0547a35ef56fbf9"},"schema_version":"1.0"},"canonical_sha256":"0a10c0295f3cbf3268af1111550c5368a02f4f4040323ee5c0cc1b0c06f46799","source":{"kind":"arxiv","id":"2504.04060","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BIIMAKK7HS7TE2FPCEIVKDCTNC","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:57:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"66164603b757c77e610e44124051ecb737f17fd632acc80f32cd77e556aca925","abstract_canon_sha256":"98b93e0c02350581f8478374d8aa64a3dd57fcff261f8273c0547a35ef56fbf9"},"schema_version":"1.0"},"canonical_sha256":"0a10c0295f3cbf3268af1111550c5368a02f4f4040323ee5c0cc1b0c06f46799","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:21.770882Z","signature_b64":"iKY/Ta/nPslFRg7Z+KI/GBvoPFHlgWggthrc/7PhT0Izt/9Q9ebN9/MzAqUPQE/aSLJEU6oIEcOkN8cYiHQmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a10c0295f3cbf3268af1111550c5368a02f4f4040323ee5c0cc1b0c06f46799","last_reissued_at":"2026-07-05T10:52:21.770413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:21.770413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04060","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewl6Xvkl8m+5MjOgME8ts9tJpY2OPW5FaaDyJ1ZedK5FbkDAQDFZwrfePAZ1nEn/lL9XXxKfqYLNC6w6L6GqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:12:04.716672Z"},"content_sha256":"510d4ae0e0988437a398f5d583daf9ec97d7cb003e9f1c8437ab48a3ab66a5cd","schema_version":"1.0","event_id":"sha256:510d4ae0e0988437a398f5d583daf9ec97d7cb003e9f1c8437ab48a3ab66a5cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BIIMAKK7HS7TE2FPCEIVKDCTNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Heyang Liu, Qunshan Gu, Ronghua Wu, Yanfeng Wang, Yuhao Wang, Yu Wang, Ziyang Cheng","submitted_at":"2025-04-05T04:57:12Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04060","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.04060/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuPk3C2HmUlyVJrFOJpgkIjXyQE7XwIltagOgFSYfP2HOzTMEV/r0GFwLNTwJ6xtdzQpDiBzxxqFQO/4XH+YBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:12:04.717596Z"},"content_sha256":"ef38abb540ba86acbeb3752c7e6c32c0f6c083f0b0d17809c5fe8fd5244272d4","schema_version":"1.0","event_id":"sha256:ef38abb540ba86acbeb3752c7e6c32c0f6c083f0b0d17809c5fe8fd5244272d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC/bundle.json","state_url":"https://pith.science/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T22:12:04Z","links":{"resolver":"https://pith.science/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC","bundle":"https://pith.science/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC/bundle.json","state":"https://pith.science/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BIIMAKK7HS7TE2FPCEIVKDCTNC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rbhCcXBef1vK5ATD+sj33jxvfwWRe+aGbriUWuby6pzj3soQ+zp1+vLObfiO9aYUSJVeywG7JsxRdAaehyHcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:12:04.723381Z","bundle_sha256":"2678caf21a127a7680a26040c0862da992301d16157f942ad8304d3598bb5662"}}