{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OSX35QR3U5YCRRBBJR6H5W7YQM","short_pith_number":"pith:OSX35QR3","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"},"canonical_sha256":"74afbec23ba77028c4214c7c7edbf8830459c0afcf8d59c4b63bf6be95e57e75","source":{"kind":"arxiv","id":"2410.03335","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03335","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03335v2","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03335","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"pith_short_12","alias_value":"OSX35QR3U5YC","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"pith_short_16","alias_value":"OSX35QR3U5YCRRBB","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"pith_short_8","alias_value":"OSX35QR3","created_at":"2026-07-05T10:00:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OSX35QR3U5YCRRBBJR6H5W7YQM","target":"record","payload":{"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"},"canonical_sha256":"74afbec23ba77028c4214c7c7edbf8830459c0afcf8d59c4b63bf6be95e57e75","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"},"source_kind":"arxiv","source_id":"2410.03335","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":"2026-07-05T10:00:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"97CX1pUEdqGj1goihkBeAhmrhVmQAmBlzalpLEiosSxNQVwsfe1/D/WikkV0behpVFbKTSb+YtTICR6GtGQFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:11:24.031725Z"},"content_sha256":"09525a7fc9fdd537b35849e2f9c0752cc55c083334fd284d0060ef39251028ba","schema_version":"1.0","event_id":"sha256:09525a7fc9fdd537b35849e2f9c0752cc55c083334fd284d0060ef39251028ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OSX35QR3U5YCRRBBJR6H5W7YQM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"659Y8doDiCwfYt5lalR7ZTAoxj7cZcRip43POAHuGcxfeqg70s4wgT/gnOZp9TNdrdXqu8vjOiTVwoStTNx1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:11:24.032618Z"},"content_sha256":"15c5cc2badafbc4c89c4d912cc144f96a712d1db0a220143ff1d085c3afa6b6b","schema_version":"1.0","event_id":"sha256:15c5cc2badafbc4c89c4d912cc144f96a712d1db0a220143ff1d085c3afa6b6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/bundle.json","state_url":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/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":"2026-08-20T12:11:24Z","links":{"resolver":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM","bundle":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/bundle.json","state":"https://pith.science/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSX35QR3U5YCRRBBJR6H5W7YQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OSX35QR3U5YCRRBBJR6H5W7YQM","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":"27c98899045e41aa164087d27871d9e3e82f791d305650eee60e735aead55416","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-04T11:40:53Z","title_canon_sha256":"88e167884f8817e98656b396659c208cac757d2c8d09905c3955937c12420036"},"schema_version":"1.0","source":{"id":"2410.03335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03335","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03335v2","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03335","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"pith_short_12","alias_value":"OSX35QR3U5YC","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"pith_short_16","alias_value":"OSX35QR3U5YCRRBB","created_at":"2026-07-05T10:00:41Z"},{"alias_kind":"pith_short_8","alias_value":"OSX35QR3","created_at":"2026-07-05T10:00:41Z"}],"graph_snapshots":[{"event_id":"sha256:15c5cc2badafbc4c89c4d912cc144f96a712d1db0a220143ff1d085c3afa6b6b","target":"graph","created_at":"2026-07-05T10:00:41Z","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/2410.03335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chi-Keung Tang, Yu-Wing Tai, Zixuan Wang","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-04T11:40:53Z","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03335","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":"sha256:09525a7fc9fdd537b35849e2f9c0752cc55c083334fd284d0060ef39251028ba","target":"record","created_at":"2026-07-05T10:00:41Z","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":"27c98899045e41aa164087d27871d9e3e82f791d305650eee60e735aead55416","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-04T11:40:53Z","title_canon_sha256":"88e167884f8817e98656b396659c208cac757d2c8d09905c3955937c12420036"},"schema_version":"1.0","source":{"id":"2410.03335","kind":"arxiv","version":2}},"canonical_sha256":"74afbec23ba77028c4214c7c7edbf8830459c0afcf8d59c4b63bf6be95e57e75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74afbec23ba77028c4214c7c7edbf8830459c0afcf8d59c4b63bf6be95e57e75","first_computed_at":"2026-07-05T10:00:41.828687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:41.828687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iOdV2sRn+Rg6g0nWQHAB8O6TZDCw92l6sZ+5cW+HVeRgJ7F6X5+ErVsn2Tnc32lvxjfLxwHUcmVJ5wU7tx0BAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:41.829124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09525a7fc9fdd537b35849e2f9c0752cc55c083334fd284d0060ef39251028ba","sha256:15c5cc2badafbc4c89c4d912cc144f96a712d1db0a220143ff1d085c3afa6b6b"],"state_sha256":"edb0aebd58e7ebaf4c27dfe9b2d30a6bc2bfca2eeb73471f7afa9ba446a5ec31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1179TJulWqAx8m/fHcNtrVsWeTQU49g3LtJ1hOhZRxJv+9yJP7P9l9tPtPDa9o4AIMzIukUgHc9GqnYyYfRAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:11:24.037646Z","bundle_sha256":"23bcb75b83fb96026cdcffdbdc19d58ae28ad1797a014293745950744f371d46"}}