{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NRK3Z5UVENI4T35O6MDWB3MKSH","short_pith_number":"pith:NRK3Z5UV","schema_version":"1.0","canonical_sha256":"6c55bcf6952351c9efaef30760ed8a91ec49479442022cd95ea7f3e867af7d2b","source":{"kind":"arxiv","id":"2310.04673","version":4},"attestation_state":"computed","paper":{"title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chang Zhou, Jiaming Wang, Jin Xu, Kai Hu, Qian Chen, Shiliang Zhang, Siqi Zheng, Wen Wang, Xiaohuan Zhou, Yunfei Chu, Zerui Li, Zhifu Gao, Zhihao Du, Zhijie Yan, Ziyang Ma","submitted_at":"2023-10-07T03:17:59Z","abstract_excerpt":"Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for audio-and-text large language models (LLMs). Previous mainstream audio-and-text LLMs use discrete audio tokens to represent both input and output audio; however, they suffer from performance degradation on tasks such as automatic speech recognition, speech-to-text translation, and speech enhancement over models using continuous speech features. In this paper, we propose LauraGPT, a novel unified audio-and-text GPT-bas"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.04673","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-07T03:17:59Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"02cdd3d0a9999b736f8b8e52a092ec8e050701b26584d250abd3497946787e4e","abstract_canon_sha256":"f0c86427eb452c89cb5e695de04f226a97f175f508fc0000cbaf0496bd2e9d74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:28.521270Z","signature_b64":"F64WvonrT2bUgswDyJUXlyiN/6RnMW6XMwDN2NnQisAYtwqCfr26ymK7qUXcqcOLVhHjo/rKtFt98PktVpP6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c55bcf6952351c9efaef30760ed8a91ec49479442022cd95ea7f3e867af7d2b","last_reissued_at":"2026-07-05T08:39:28.520858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:28.520858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chang Zhou, Jiaming Wang, Jin Xu, Kai Hu, Qian Chen, Shiliang Zhang, Siqi Zheng, Wen Wang, Xiaohuan Zhou, Yunfei Chu, Zerui Li, Zhifu Gao, Zhihao Du, Zhijie Yan, Ziyang Ma","submitted_at":"2023-10-07T03:17:59Z","abstract_excerpt":"Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for audio-and-text large language models (LLMs). Previous mainstream audio-and-text LLMs use discrete audio tokens to represent both input and output audio; however, they suffer from performance degradation on tasks such as automatic speech recognition, speech-to-text translation, and speech enhancement over models using continuous speech features. In this paper, we propose LauraGPT, a novel unified audio-and-text GPT-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04673","kind":"arxiv","version":4},"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/2310.04673/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.04673","created_at":"2026-07-05T08:39:28.520913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04673v4","created_at":"2026-07-05T08:39:28.520913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04673","created_at":"2026-07-05T08:39:28.520913+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRK3Z5UVENI4","created_at":"2026-07-05T08:39:28.520913+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRK3Z5UVENI4T35O","created_at":"2026-07-05T08:39:28.520913+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRK3Z5UV","created_at":"2026-07-05T08:39:28.520913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23190","citing_title":"FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06559","citing_title":"IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29675","citing_title":"From Prompts to Context: An Ontology-Driven Framework for Human-Generative AI Collaboration","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14294","citing_title":"DASB - Discrete Audio and Speech Benchmark","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06006","citing_title":"Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23511","citing_title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19635","citing_title":"StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH","json":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH.json","graph_json":"https://pith.science/api/pith-number/NRK3Z5UVENI4T35O6MDWB3MKSH/graph.json","events_json":"https://pith.science/api/pith-number/NRK3Z5UVENI4T35O6MDWB3MKSH/events.json","paper":"https://pith.science/paper/NRK3Z5UV"},"agent_actions":{"view_html":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH","download_json":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH.json","view_paper":"https://pith.science/paper/NRK3Z5UV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04673&json=true","fetch_graph":"https://pith.science/api/pith-number/NRK3Z5UVENI4T35O6MDWB3MKSH/graph.json","fetch_events":"https://pith.science/api/pith-number/NRK3Z5UVENI4T35O6MDWB3MKSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH/action/storage_attestation","attest_author":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH/action/author_attestation","sign_citation":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH/action/citation_signature","submit_replication":"https://pith.science/pith/NRK3Z5UVENI4T35O6MDWB3MKSH/action/replication_record"}},"created_at":"2026-07-05T08:39:28.520913+00:00","updated_at":"2026-07-05T08:39:28.520913+00:00"}