{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NNVQZHTTJXEN4F3U7D4OIAGZDL","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":"4c6a3b2a666c14cc10f054122a32e5f886d966b47344e0e1a32b8ebe60d03d94","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-17T14:16:24Z","title_canon_sha256":"827f61043f4dfe22dfff297bec6fbab69a245256f9cb6405e4b2d75c6a2439ad"},"schema_version":"1.0","source":{"id":"2306.10359","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10359","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10359v5","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10359","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"NNVQZHTTJXEN","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"NNVQZHTTJXEN4F3U","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"NNVQZHTT","created_at":"2026-07-05T06:51:26Z"}],"graph_snapshots":[{"event_id":"sha256:448e4b821791b0643c4ba5ac2ed88e4ec6e37c897afb73895a7115366e0cd44f","target":"graph","created_at":"2026-07-05T06:51:26Z","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/2306.10359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foley sound generation aims to synthesise the background sound for multimedia content. Previous models usually employ a large development set with labels as input (e.g., single numbers or one-hot vector). In this work, we propose a diffusion model based system for Foley sound generation with text conditions. To alleviate the data scarcity issue, our model is initially pre-trained with large-scale datasets and fine-tuned to this task via transfer learning using the contrastive language-audio pertaining (CLAP) technique. We have observed that the feature embedding extracted by the text encoder c","authors_text":"Haohe Liu, Mark D. Plumbley, Peipei Wu, Wenwu Wang, Xiyuan Kang, Xubo Liu, Yi Yuan","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-17T14:16:24Z","title":"Text-Driven Foley Sound Generation With Latent Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10359","kind":"arxiv","version":5},"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:fe6b0a014cc21f2da6520127a6e7c84d0452d78a77a9db80444c3026a2ff8e78","target":"record","created_at":"2026-07-05T06:51:26Z","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":"4c6a3b2a666c14cc10f054122a32e5f886d966b47344e0e1a32b8ebe60d03d94","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-17T14:16:24Z","title_canon_sha256":"827f61043f4dfe22dfff297bec6fbab69a245256f9cb6405e4b2d75c6a2439ad"},"schema_version":"1.0","source":{"id":"2306.10359","kind":"arxiv","version":5}},"canonical_sha256":"6b6b0c9e734dc8de1774f8f8e400d91ad50069d14ead97263f90d8eed1803644","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b6b0c9e734dc8de1774f8f8e400d91ad50069d14ead97263f90d8eed1803644","first_computed_at":"2026-07-05T06:51:26.776232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:26.776232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvBIYm9jUad1vuo8J5a+mzYd+UOe/YkjGuTuypumZ/L2cA21jbiptooqt3P09p45FtlabwkkE4gbmxzBDLfmDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:26.776814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10359","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe6b0a014cc21f2da6520127a6e7c84d0452d78a77a9db80444c3026a2ff8e78","sha256:448e4b821791b0643c4ba5ac2ed88e4ec6e37c897afb73895a7115366e0cd44f"],"state_sha256":"30e917b854b815b282081ebef585623c7a448ae3223fe11404fb3531af7a8879"}