{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XBII5KLB6FQQBGLHBUADOVR2ZD","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":"a5fc268826b665a14162c392e5994ff55aa26f498a8ba2da6f5246d10941dbde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-14T16:10:34Z","title_canon_sha256":"a977aef4d39bb3ce0dbe671f31500983d9b82da853095f77a97783027fdb33a3"},"schema_version":"1.0","source":{"id":"2403.09527","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09527","created_at":"2026-07-05T08:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09527v3","created_at":"2026-07-05T08:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09527","created_at":"2026-07-05T08:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"XBII5KLB6FQQ","created_at":"2026-07-05T08:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"XBII5KLB6FQQBGLH","created_at":"2026-07-05T08:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"XBII5KLB","created_at":"2026-07-05T08:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:df5543ff6560c63edc50509441ca6cc31d1d79a34c77074a4b9985f9b058727b","target":"graph","created_at":"2026-07-05T08:17:31Z","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/2403.09527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing. Specifically, WavCraft describes the content of raw audio materials in natural language and prompts the LLM conditioned on audio descriptions and user requests. WavCraft leverages the in-context learning ability of the LLM to decomposes users' instructions into several tasks and tackle each task collaboratively with the particular module. Through task decomposition along with a set of task-specific models, WavCraft follows the in","authors_text":"Emmanouil Benetos, Haohe Liu, Huan Zhang, Huy Phan, Jinhua Liang, Mark D. Plumbley, Qiuqiang Kong, Wenwu Wang, Xubo Liu, Yin Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-14T16:10:34Z","title":"WavCraft: Audio Editing and Generation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09527","kind":"arxiv","version":3},"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":"sha256:98837be01f8ee51d4f97cc558225bad4debe1abb9dd2f2ff04955e192ff4d25a","target":"record","created_at":"2026-07-05T08:17:31Z","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":"a5fc268826b665a14162c392e5994ff55aa26f498a8ba2da6f5246d10941dbde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-14T16:10:34Z","title_canon_sha256":"a977aef4d39bb3ce0dbe671f31500983d9b82da853095f77a97783027fdb33a3"},"schema_version":"1.0","source":{"id":"2403.09527","kind":"arxiv","version":3}},"canonical_sha256":"b8508ea961f1610099670d0037563ac8e5cee22d7c6f1aa2f4e4a2d27c67a91c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8508ea961f1610099670d0037563ac8e5cee22d7c6f1aa2f4e4a2d27c67a91c","first_computed_at":"2026-07-05T08:17:31.619603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:31.619603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i6hbFFv69btFDHioxrA2GLvN8k+Oz0d6abPrazz+nWJXzoI5nVlqasvdqxTtc/ymDEPP5Xel8qvWP7NrCo6SBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:31.620114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09527","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98837be01f8ee51d4f97cc558225bad4debe1abb9dd2f2ff04955e192ff4d25a","sha256:df5543ff6560c63edc50509441ca6cc31d1d79a34c77074a4b9985f9b058727b"],"state_sha256":"f81a3633054eded5143ed9d59ff1c5714b325bb2dd271ba1834f8e15f6b33565"}