{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YEYZXR2PT4AJQCRZZODU7P4KTM","short_pith_number":"pith:YEYZXR2P","canonical_record":{"source":{"id":"2410.08035","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T05:04:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fd23aafa27e07912e6a4ebeab7b59c228821ba3471046279738f453815bf6e0","abstract_canon_sha256":"dd9554665de751c1c06e493cdf3797a18a0a4df39b3a6b3e5ab85586da4b95e4"},"schema_version":"1.0"},"canonical_sha256":"c1319bc74f9f00980a39cb874fbf8a9b254367369807a96d441c125b7a6bfdac","source":{"kind":"arxiv","id":"2410.08035","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08035","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08035v2","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08035","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"pith_short_12","alias_value":"YEYZXR2PT4AJ","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"pith_short_16","alias_value":"YEYZXR2PT4AJQCRZ","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"pith_short_8","alias_value":"YEYZXR2P","created_at":"2026-07-05T09:19:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YEYZXR2PT4AJQCRZZODU7P4KTM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08035","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T05:04:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fd23aafa27e07912e6a4ebeab7b59c228821ba3471046279738f453815bf6e0","abstract_canon_sha256":"dd9554665de751c1c06e493cdf3797a18a0a4df39b3a6b3e5ab85586da4b95e4"},"schema_version":"1.0"},"canonical_sha256":"c1319bc74f9f00980a39cb874fbf8a9b254367369807a96d441c125b7a6bfdac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:33.308352Z","signature_b64":"H5p7UwzBIVH4pvk13XzSe1cEHQ2kTQ49MI4mdBimtWkz9TlTAWcLbl6znb90lPjHidzBhQK+6mbJXKn4W8ZHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1319bc74f9f00980a39cb874fbf8a9b254367369807a96d441c125b7a6bfdac","last_reissued_at":"2026-07-05T09:19:33.307858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:33.307858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08035","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":"2026-07-05T09:19:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dlzYiv+2u2Tuaxon184AsHrLI9zl7ZtSaABW4FpTwxTI7Y4dakM1kpLktuYXwmZNd6vopQTA1ycr7/hQXTesAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:44:59.540849Z"},"content_sha256":"75cae8a94af87fd996a8552d7bb272bba8857156d2de8b3a25ecbcf58f717370","schema_version":"1.0","event_id":"sha256:75cae8a94af87fd996a8552d7bb272bba8857156d2de8b3a25ecbcf58f717370"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YEYZXR2PT4AJQCRZZODU7P4KTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Bin Zhang, Chaohong Tan, Dong Zhang, Hangrui Hu, Heng Lu, Qian Chen, Tianyu Zhao, Xiang Lyu, Xin Zhang, Xipeng Qiu, Yaqian Zhou, Yuxuan Wang, Zhihao Du","submitted_at":"2024-10-09T05:04:31Z","abstract_excerpt":"Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions. To address this, we introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interaction capabilities. IntrinsicVoice aims to facilitate the transfer of textual capabilities of pre-trained LLMs to the speech modality by mitigating the modality gap between text and speech. Our novelty a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08035","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/2410.08035/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":"2026-07-05T09:19:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"balEGbZlFiaW6NObZw0P/WUb4AyXIsbjcXzAhidE2SSH7oDOPruL2ZMtoMGRFKBTR6e+D7A3MXHkFHcRVCsSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:44:59.541399Z"},"content_sha256":"06f39e110f0791731369ba7fa11c4628f4fd75da0328ab32798be8b263db72b5","schema_version":"1.0","event_id":"sha256:06f39e110f0791731369ba7fa11c4628f4fd75da0328ab32798be8b263db72b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEYZXR2PT4AJQCRZZODU7P4KTM/bundle.json","state_url":"https://pith.science/pith/YEYZXR2PT4AJQCRZZODU7P4KTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEYZXR2PT4AJQCRZZODU7P4KTM/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":"2026-08-23T11:44:59Z","links":{"resolver":"https://pith.science/pith/YEYZXR2PT4AJQCRZZODU7P4KTM","bundle":"https://pith.science/pith/YEYZXR2PT4AJQCRZZODU7P4KTM/bundle.json","state":"https://pith.science/pith/YEYZXR2PT4AJQCRZZODU7P4KTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEYZXR2PT4AJQCRZZODU7P4KTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEYZXR2PT4AJQCRZZODU7P4KTM","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":"dd9554665de751c1c06e493cdf3797a18a0a4df39b3a6b3e5ab85586da4b95e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T05:04:31Z","title_canon_sha256":"2fd23aafa27e07912e6a4ebeab7b59c228821ba3471046279738f453815bf6e0"},"schema_version":"1.0","source":{"id":"2410.08035","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08035","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08035v2","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08035","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"pith_short_12","alias_value":"YEYZXR2PT4AJ","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"pith_short_16","alias_value":"YEYZXR2PT4AJQCRZ","created_at":"2026-07-05T09:19:33Z"},{"alias_kind":"pith_short_8","alias_value":"YEYZXR2P","created_at":"2026-07-05T09:19:33Z"}],"graph_snapshots":[{"event_id":"sha256:06f39e110f0791731369ba7fa11c4628f4fd75da0328ab32798be8b263db72b5","target":"graph","created_at":"2026-07-05T09:19:33Z","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/2410.08035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions. To address this, we introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interaction capabilities. IntrinsicVoice aims to facilitate the transfer of textual capabilities of pre-trained LLMs to the speech modality by mitigating the modality gap between text and speech. Our novelty a","authors_text":"Bin Zhang, Chaohong Tan, Dong Zhang, Hangrui Hu, Heng Lu, Qian Chen, Tianyu Zhao, Xiang Lyu, Xin Zhang, Xipeng Qiu, Yaqian Zhou, Yuxuan Wang, Zhihao Du","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T05:04:31Z","title":"IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08035","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":"sha256:75cae8a94af87fd996a8552d7bb272bba8857156d2de8b3a25ecbcf58f717370","target":"record","created_at":"2026-07-05T09:19:33Z","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":"dd9554665de751c1c06e493cdf3797a18a0a4df39b3a6b3e5ab85586da4b95e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-09T05:04:31Z","title_canon_sha256":"2fd23aafa27e07912e6a4ebeab7b59c228821ba3471046279738f453815bf6e0"},"schema_version":"1.0","source":{"id":"2410.08035","kind":"arxiv","version":2}},"canonical_sha256":"c1319bc74f9f00980a39cb874fbf8a9b254367369807a96d441c125b7a6bfdac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1319bc74f9f00980a39cb874fbf8a9b254367369807a96d441c125b7a6bfdac","first_computed_at":"2026-07-05T09:19:33.307858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:33.307858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H5p7UwzBIVH4pvk13XzSe1cEHQ2kTQ49MI4mdBimtWkz9TlTAWcLbl6znb90lPjHidzBhQK+6mbJXKn4W8ZHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:33.308352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08035","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75cae8a94af87fd996a8552d7bb272bba8857156d2de8b3a25ecbcf58f717370","sha256:06f39e110f0791731369ba7fa11c4628f4fd75da0328ab32798be8b263db72b5"],"state_sha256":"1b0949b8c02ae2863616c165cb4ba378480571a07efa4f318f8842fe41d67742"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRYKgamZovyjT0MQKi9eolzXfndjoHHsUbjCxpWdFiyIfSSePM5QcDo6JbEFrhbPPqx7ylYlNXBJffNPf+2ZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T11:44:59.546256Z","bundle_sha256":"21baf6844c823b6a2da32d4e434dc8dcf6b4b9ebd4d11c6d1ff904e5b21bef41"}}