{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ONF4QBSIYPJN2K3TBEXS5MNWVM","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":"f41a733c7e8cadb1ceeebd8fe8356b82447baa2e0f2088e5ce8540e38f723ef6","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-26T17:54:04Z","title_canon_sha256":"96fed8277e81c2d7e602d2583ff3ef259d8be69984d9968fe349b73d46832202"},"schema_version":"1.0","source":{"id":"2307.14335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14335","created_at":"2026-07-05T07:16:44Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14335v2","created_at":"2026-07-05T07:16:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14335","created_at":"2026-07-05T07:16:44Z"},{"alias_kind":"pith_short_12","alias_value":"ONF4QBSIYPJN","created_at":"2026-07-05T07:16:44Z"},{"alias_kind":"pith_short_16","alias_value":"ONF4QBSIYPJN2K3T","created_at":"2026-07-05T07:16:44Z"},{"alias_kind":"pith_short_8","alias_value":"ONF4QBSI","created_at":"2026-07-05T07:16:44Z"}],"graph_snapshots":[{"event_id":"sha256:df726a37b5fdc44b8a470aa71fec8d3faaa026800f0dc593757fc248eeceeaba","target":"graph","created_at":"2026-07-05T07:16:44Z","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/2307.14335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite breakthroughs in audio generation models, their capabilities are often confined to domain-specific conditions such as speech transcriptions and audio captions. However, real-world audio creation aims to generate harmonious audio containing various elements such as speech, music, and sound effects with controllable conditions, which is challenging to address using existing audio generation systems. We present WavJourney, a novel framework that leverages Large Language Models (LLMs) to connect various audio models for audio creation. WavJourney allows users to create storytelling audio c","authors_text":"Haohe Liu, Jinhua Liang, Mark D. Plumbley, Meng Cui, Qiuqiang Kong, Qiushi Huang, Wenwu Wang, Xubo Liu, Yin Cao, Yi Yuan, Zhongkai Zhu","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-26T17:54:04Z","title":"WavJourney: Compositional Audio Creation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14335","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:e54046e25be2b28208ae1c2bd63026df1e6b1b98292000ef8153f2d2cab51429","target":"record","created_at":"2026-07-05T07:16:44Z","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":"f41a733c7e8cadb1ceeebd8fe8356b82447baa2e0f2088e5ce8540e38f723ef6","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-26T17:54:04Z","title_canon_sha256":"96fed8277e81c2d7e602d2583ff3ef259d8be69984d9968fe349b73d46832202"},"schema_version":"1.0","source":{"id":"2307.14335","kind":"arxiv","version":2}},"canonical_sha256":"734bc80648c3d2dd2b73092f2eb1b6ab1b032a556bc5d0bf695c27431fe21547","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"734bc80648c3d2dd2b73092f2eb1b6ab1b032a556bc5d0bf695c27431fe21547","first_computed_at":"2026-07-05T07:16:44.519665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:44.519665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/lBpHFCwcnHhjhwt7XCn2s6kWWTrB6FnXT/EbCWVT33NPyxkXBQlQpWpsvS7+GEdwz8ZSn0XZ8UMTuUprumAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:44.520176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e54046e25be2b28208ae1c2bd63026df1e6b1b98292000ef8153f2d2cab51429","sha256:df726a37b5fdc44b8a470aa71fec8d3faaa026800f0dc593757fc248eeceeaba"],"state_sha256":"915be3d4c9e824fe8d89db865418b89725ede4c831b86a3069d0227a7a5479f5"}