{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:26CCG7ZKZW44TZPVCJ5VN5QPJD","short_pith_number":"pith:26CCG7ZK","canonical_record":{"source":{"id":"2304.12995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-25T17:05:38Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"b4d0445ca42ae2b89619c773a0371124d3464f7392c760e0ac6a085fe76eba01","abstract_canon_sha256":"2288dcf42599ffeb7f9885df0b92a7bcaad80d0b89ae7c54233c299d2e7fb38e"},"schema_version":"1.0"},"canonical_sha256":"d784237f2acdb9c9e5f5127b56f60f48fbe97e1f34d9cf835c937a05a30e6267","source":{"kind":"arxiv","id":"2304.12995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12995","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12995v1","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12995","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"26CCG7ZKZW44","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"26CCG7ZKZW44TZPV","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"26CCG7ZK","created_at":"2026-07-05T06:04:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:26CCG7ZKZW44TZPVCJ5VN5QPJD","target":"record","payload":{"canonical_record":{"source":{"id":"2304.12995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-25T17:05:38Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"b4d0445ca42ae2b89619c773a0371124d3464f7392c760e0ac6a085fe76eba01","abstract_canon_sha256":"2288dcf42599ffeb7f9885df0b92a7bcaad80d0b89ae7c54233c299d2e7fb38e"},"schema_version":"1.0"},"canonical_sha256":"d784237f2acdb9c9e5f5127b56f60f48fbe97e1f34d9cf835c937a05a30e6267","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:23.207979Z","signature_b64":"aB8EUNj84cIWj0vu/YNERf+uZsLw4VQtyBkRCF3fl/GNKTNb8NQNnczT7GHcQP8WpEghZrBbqpz/L9fVahYGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d784237f2acdb9c9e5f5127b56f60f48fbe97e1f34d9cf835c937a05a30e6267","last_reissued_at":"2026-07-05T06:04:23.207573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:23.207573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.12995","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:04:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rqwrsoxCrFdMG8j6BlIrhczHpchHlK5GlFpPvnKxjU5PvA/FVtjspPAoxTL5DdBEDz55e2qPFEwVp38h0ELlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:15:54.105957Z"},"content_sha256":"03f2eabb19ec90162374804b82ae6feabef8d2f1a87d59cf9a8351fc5a6954e4","schema_version":"1.0","event_id":"sha256:03f2eabb19ec90162374804b82ae6feabef8d2f1a87d59cf9a8351fc5a6954e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:26CCG7ZKZW44TZPVCJ5VN5QPJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongchao Yang, Jiatong Shi, Jiawei Huang, Jinglin Liu, Mingze Li, Rongjie Huang, Shinji Watanabe, Xuankai Chang, Yi Ren, Yuning Wu, Zhenhui Ye, Zhiqing Hong, Zhou Zhao","submitted_at":"2023-04-25T17:05:38Z","abstract_excerpt":"Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12995","kind":"arxiv","version":1},"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/2304.12995/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":"2026-07-05T06:04:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nnvM02nBou9GzT98CXPdM/XCCsuIZ+KHG/JUbPWzVmCbhXtyQJKj5lhpk0dlsvZpdcZwU33+0S6Aq9ale1olBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:15:54.106485Z"},"content_sha256":"571220b1cf4a03f236ae0c85c674aea716b73d6be228164e6c1e4075f4889351","schema_version":"1.0","event_id":"sha256:571220b1cf4a03f236ae0c85c674aea716b73d6be228164e6c1e4075f4889351"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD/bundle.json","state_url":"https://pith.science/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD/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":"2026-08-04T10:15:54Z","links":{"resolver":"https://pith.science/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD","bundle":"https://pith.science/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD/bundle.json","state":"https://pith.science/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26CCG7ZKZW44TZPVCJ5VN5QPJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:26CCG7ZKZW44TZPVCJ5VN5QPJD","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":"2288dcf42599ffeb7f9885df0b92a7bcaad80d0b89ae7c54233c299d2e7fb38e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-25T17:05:38Z","title_canon_sha256":"b4d0445ca42ae2b89619c773a0371124d3464f7392c760e0ac6a085fe76eba01"},"schema_version":"1.0","source":{"id":"2304.12995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12995","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12995v1","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12995","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"26CCG7ZKZW44","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"26CCG7ZKZW44TZPV","created_at":"2026-07-05T06:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"26CCG7ZK","created_at":"2026-07-05T06:04:23Z"}],"graph_snapshots":[{"event_id":"sha256:571220b1cf4a03f236ae0c85c674aea716b73d6be228164e6c1e4075f4889351","target":"graph","created_at":"2026-07-05T06:04:23Z","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/2304.12995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spok","authors_text":"Dongchao Yang, Jiatong Shi, Jiawei Huang, Jinglin Liu, Mingze Li, Rongjie Huang, Shinji Watanabe, Xuankai Chang, Yi Ren, Yuning Wu, Zhenhui Ye, Zhiqing Hong, Zhou Zhao","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-25T17:05:38Z","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12995","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":"sha256:03f2eabb19ec90162374804b82ae6feabef8d2f1a87d59cf9a8351fc5a6954e4","target":"record","created_at":"2026-07-05T06:04:23Z","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":"2288dcf42599ffeb7f9885df0b92a7bcaad80d0b89ae7c54233c299d2e7fb38e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-25T17:05:38Z","title_canon_sha256":"b4d0445ca42ae2b89619c773a0371124d3464f7392c760e0ac6a085fe76eba01"},"schema_version":"1.0","source":{"id":"2304.12995","kind":"arxiv","version":1}},"canonical_sha256":"d784237f2acdb9c9e5f5127b56f60f48fbe97e1f34d9cf835c937a05a30e6267","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d784237f2acdb9c9e5f5127b56f60f48fbe97e1f34d9cf835c937a05a30e6267","first_computed_at":"2026-07-05T06:04:23.207573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:23.207573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aB8EUNj84cIWj0vu/YNERf+uZsLw4VQtyBkRCF3fl/GNKTNb8NQNnczT7GHcQP8WpEghZrBbqpz/L9fVahYGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:23.207979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03f2eabb19ec90162374804b82ae6feabef8d2f1a87d59cf9a8351fc5a6954e4","sha256:571220b1cf4a03f236ae0c85c674aea716b73d6be228164e6c1e4075f4889351"],"state_sha256":"6aad97b302bce3a994f4554c911f46e60acb6c3cc5f8b52fee1f168d7b595578"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9armM+XCugHEa08bxEzZMcFMk2of0C8DDk8g3GiEkUX7v8BII3sF+0He/hnBf9/Ce0r4XBfnqVLDkuLHu50Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:15:54.110447Z","bundle_sha256":"bf89a3eeb5c0c761ae05bf9c2948378c1f13679d4882a48841b0ca0dd649f43b"}}