{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M5PNVHOTEQBSTKJOJFALHSYJXH","short_pith_number":"pith:M5PNVHOT","canonical_record":{"source":{"id":"2407.04051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T16:49:02Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"12a9b1b0f0e56d65b62e51c57a72faba69b2f63847cabbf6eebe3abcc93afe71","abstract_canon_sha256":"6d65ee4981ce17d499fe6a6b6b791b8581ea73f9df9692bc8597236ffe9d35d7"},"schema_version":"1.0"},"canonical_sha256":"675eda9dd3240329a92e4940b3cb09b9c9e316a93e0270fad8a07cb60a637340","source":{"kind":"arxiv","id":"2407.04051","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04051","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04051v3","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04051","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"M5PNVHOTEQBS","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_16","alias_value":"M5PNVHOTEQBSTKJO","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_8","alias_value":"M5PNVHOT","created_at":"2026-07-05T08:42:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M5PNVHOTEQBSTKJOJFALHSYJXH","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04051","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T16:49:02Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"12a9b1b0f0e56d65b62e51c57a72faba69b2f63847cabbf6eebe3abcc93afe71","abstract_canon_sha256":"6d65ee4981ce17d499fe6a6b6b791b8581ea73f9df9692bc8597236ffe9d35d7"},"schema_version":"1.0"},"canonical_sha256":"675eda9dd3240329a92e4940b3cb09b9c9e316a93e0270fad8a07cb60a637340","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:38.299200Z","signature_b64":"xNjyKFMvFpprOQ2ijq6F6pJT87T5siGGVWOddRIE/Pcpo5KIYwkzQ0JvEBftXQOjTM5ci5Jxbq1wCKRDbgCZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675eda9dd3240329a92e4940b3cb09b9c9e316a93e0270fad8a07cb60a637340","last_reissued_at":"2026-07-05T08:42:38.298698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:38.298698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04051","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uB6L13OcH9nzOwnPjfaiSAWtIsU7LftSLd8I5BsU2jeZdDFR7wt2dHCuqZk5CDIsA+0T5BPL44aXskqSbDOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:56:51.649300Z"},"content_sha256":"41cdce2df8b4c10b1a732ce63c4e2ca6115f60dc50a21db6de7da0353f44fe0e","schema_version":"1.0","event_id":"sha256:41cdce2df8b4c10b1a732ce63c4e2ca6115f60dc50a21db6de7da0353f44fe0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M5PNVHOTEQBSTKJOJFALHSYJXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Bin Zhang, Changfeng Gao, Changhe Song, Chong Deng, Chongjia Ni, Hangrui Hu, Haoneng Luo, Hao Wang, Heng Lu, Jiaqi Shi, Kai Hu, Keyu An, Nan Zhao, Qian Chen, Qinglin Zhang, Shengpeng Ji, Shiliang Zhang, Siqi Zheng, Ting He, Wen Wang, Xiang Lv, Xian Shi, Yabin Li, Yexin Yang, Yue Gu, Yuxuan Wang, Zerui Li, Zhangyu Xiao, Zhifu Gao, Zhihao Du, Zhijie Yan, Ziyang Ma","submitted_at":"2024-07-04T16:49:02Z","abstract_excerpt":"This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. SenseVoice-Small delivers exceptionally low-latency ASR for 5 languages, and SenseVoice-Large supports high-precision ASR for over 50 languages, while CosyVoice exc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04051","kind":"arxiv","version":3},"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/2407.04051/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":"2026-07-05T08:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9x72Vr5Odj9eUFvjnVSkLwVYmpm42ja0+Dnu3iDeuw8qkA1oVDKLuQmXElfANpUyHEP5I0lwYmYUvX1f3bW2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:56:51.649695Z"},"content_sha256":"64cb238b63f049af5a6e160d6ee89733920994e3339ce27a448dd663a8922e48","schema_version":"1.0","event_id":"sha256:64cb238b63f049af5a6e160d6ee89733920994e3339ce27a448dd663a8922e48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5PNVHOTEQBSTKJOJFALHSYJXH/bundle.json","state_url":"https://pith.science/pith/M5PNVHOTEQBSTKJOJFALHSYJXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5PNVHOTEQBSTKJOJFALHSYJXH/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":"2026-07-07T07:56:51Z","links":{"resolver":"https://pith.science/pith/M5PNVHOTEQBSTKJOJFALHSYJXH","bundle":"https://pith.science/pith/M5PNVHOTEQBSTKJOJFALHSYJXH/bundle.json","state":"https://pith.science/pith/M5PNVHOTEQBSTKJOJFALHSYJXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5PNVHOTEQBSTKJOJFALHSYJXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M5PNVHOTEQBSTKJOJFALHSYJXH","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":"6d65ee4981ce17d499fe6a6b6b791b8581ea73f9df9692bc8597236ffe9d35d7","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T16:49:02Z","title_canon_sha256":"12a9b1b0f0e56d65b62e51c57a72faba69b2f63847cabbf6eebe3abcc93afe71"},"schema_version":"1.0","source":{"id":"2407.04051","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04051","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04051v3","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04051","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"M5PNVHOTEQBS","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_16","alias_value":"M5PNVHOTEQBSTKJO","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_8","alias_value":"M5PNVHOT","created_at":"2026-07-05T08:42:38Z"}],"graph_snapshots":[{"event_id":"sha256:64cb238b63f049af5a6e160d6ee89733920994e3339ce27a448dd663a8922e48","target":"graph","created_at":"2026-07-05T08:42:38Z","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/2407.04051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. SenseVoice-Small delivers exceptionally low-latency ASR for 5 languages, and SenseVoice-Large supports high-precision ASR for over 50 languages, while CosyVoice exc","authors_text":"Bin Ma, Bin Zhang, Changfeng Gao, Changhe Song, Chong Deng, Chongjia Ni, Hangrui Hu, Haoneng Luo, Hao Wang, Heng Lu, Jiaqi Shi, Kai Hu, Keyu An, Nan Zhao, Qian Chen, Qinglin Zhang, Shengpeng Ji, Shiliang Zhang, Siqi Zheng, Ting He, Wen Wang, Xiang Lv, Xian Shi, Yabin Li, Yexin Yang, Yue Gu, Yuxuan Wang, Zerui Li, Zhangyu Xiao, Zhifu Gao, Zhihao Du, Zhijie Yan, Ziyang Ma","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T16:49:02Z","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04051","kind":"arxiv","version":3},"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":"sha256:41cdce2df8b4c10b1a732ce63c4e2ca6115f60dc50a21db6de7da0353f44fe0e","target":"record","created_at":"2026-07-05T08:42:38Z","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":"6d65ee4981ce17d499fe6a6b6b791b8581ea73f9df9692bc8597236ffe9d35d7","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T16:49:02Z","title_canon_sha256":"12a9b1b0f0e56d65b62e51c57a72faba69b2f63847cabbf6eebe3abcc93afe71"},"schema_version":"1.0","source":{"id":"2407.04051","kind":"arxiv","version":3}},"canonical_sha256":"675eda9dd3240329a92e4940b3cb09b9c9e316a93e0270fad8a07cb60a637340","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"675eda9dd3240329a92e4940b3cb09b9c9e316a93e0270fad8a07cb60a637340","first_computed_at":"2026-07-05T08:42:38.298698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:38.298698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xNjyKFMvFpprOQ2ijq6F6pJT87T5siGGVWOddRIE/Pcpo5KIYwkzQ0JvEBftXQOjTM5ci5Jxbq1wCKRDbgCZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:38.299200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04051","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41cdce2df8b4c10b1a732ce63c4e2ca6115f60dc50a21db6de7da0353f44fe0e","sha256:64cb238b63f049af5a6e160d6ee89733920994e3339ce27a448dd663a8922e48"],"state_sha256":"20431cf51a49d72212d66d2ddcbe855aee7a2bd3b8a1d0bbcd50ecc1349fb652"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pp4hW8vtgXEM6AHeyGta5NdwC5JX0HUQFqDmguIgC1f8hdCmFk5+D1an+tUDb8PFZkjKFBsvjLLt9EXe72QjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:56:51.651726Z","bundle_sha256":"48d64c01a69c641d868c27d6e79a85612c1a52b43ba5dd6ad54b962c625bc684"}}