{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OSX35QR3U5YCRRBBJR6H5W7YQM","short_pith_number":"pith:OSX35QR3","schema_version":"1.0","canonical_sha256":"74afbec23ba77028c4214c7c7edbf8830459c0afcf8d59c4b63bf6be95e57e75","source":{"kind":"arxiv","id":"2410.03335","version":2},"attestation_state":"computed","paper":{"title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chi-Keung Tang, Yu-Wing Tai, Zixuan Wang","submitted_at":"2024-10-04T11:40:53Z","abstract_excerpt":"We introduce Audio-Agent, a multimodal framework for audio generation, editing and composition based on text or video inputs. Conventional approaches for text-to-audio (TTA) tasks often make single-pass inferences from text descriptions. While straightforward, this design struggles to produce high-quality audio when given complex text conditions. In our method, we utilize a pre-trained TTA diffusion network as the audio generation agent to work in tandem with GPT-4, which decomposes the text condition into atomic, specific instructions and calls the agent for audio generation. In doing so, Aud"},"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":"2410.03335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-04T11:40:53Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"88e167884f8817e98656b396659c208cac757d2c8d09905c3955937c12420036","abstract_canon_sha256":"27c98899045e41aa164087d27871d9e3e82f791d305650eee60e735aead55416"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:41.829124Z","signature_b64":"iOdV2sRn+Rg6g0nWQHAB8O6TZDCw92l6sZ+5cW+HVeRgJ7F6X5+ErVsn2Tnc32lvxjfLxwHUcmVJ5wU7tx0BAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74afbec23ba77028c4214c7c7edbf8830459c0afcf8d59c4b63bf6be95e57e75","last_reissued_at":"2026-07-05T10:00:41.828687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:41.828687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chi-Keung Tang, Yu-Wing Tai, Zixuan Wang","submitted_at":"2024-10-04T11:40:53Z","abstract_excerpt":"We introduce Audio-Agent, a multimodal framework for audio generation, editing and composition based on text or video inputs. Conventional approaches for text-to-audio (TTA) tasks often make single-pass inferences from text descriptions. While straightforward, this design struggles to produce high-quality audio when given complex text conditions. In our method, we utilize a pre-trained TTA diffusion network as the audio generation agent to work in tandem with GPT-4, which decomposes the text condition into atomic, specific instructions and calls the agent for audio generation. In doing so, Aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03335","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/2410.03335/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":"2410.03335","created_at":"2026-07-05T10:00:41.828751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03335v2","created_at":"2026-07-05T10:00:41.828751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03335","created_at":"2026-07-05T10:00:41.828751+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSX35QR3U5YC","created_at":"2026-07-05T10:00:41.828751+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSX35QR3U5YCRRBB","created_at":"2026-07-05T10:00:41.828751+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSX35QR3","created_at":"2026-07-05T10:00:41.828751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20101","citing_title":"RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20101","citing_title":"RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM","json":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM.json","graph_json":"https://pith.science/api/pith-number/OSX35QR3U5YCRRBBJR6H5W7YQM/graph.json","events_json":"https://pith.science/api/pith-number/OSX35QR3U5YCRRBBJR6H5W7YQM/events.json","paper":"https://pith.science/paper/OSX35QR3"},"agent_actions":{"view_html":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM","download_json":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM.json","view_paper":"https://pith.science/paper/OSX35QR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03335&json=true","fetch_graph":"https://pith.science/api/pith-number/OSX35QR3U5YCRRBBJR6H5W7YQM/graph.json","fetch_events":"https://pith.science/api/pith-number/OSX35QR3U5YCRRBBJR6H5W7YQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/action/storage_attestation","attest_author":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/action/author_attestation","sign_citation":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/action/citation_signature","submit_replication":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/action/replication_record"}},"created_at":"2026-07-05T10:00:41.828751+00:00","updated_at":"2026-07-05T10:00:41.828751+00:00"}