{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EMU6PAKHDVH2KTENXE6U6GLP3P","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":"a36985d69839c448f5cc82ec70ae6194a5f735d2f672e5882a4696d97281ce3b","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T11:33:43Z","title_canon_sha256":"f908c71bfc7e365e8945bd64dc80bb7ecadb2b6dadde30a6670f4a7c568f0682"},"schema_version":"1.0","source":{"id":"2309.10537","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10537","created_at":"2026-07-05T06:52:13Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10537v1","created_at":"2026-07-05T06:52:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10537","created_at":"2026-07-05T06:52:13Z"},{"alias_kind":"pith_short_12","alias_value":"EMU6PAKHDVH2","created_at":"2026-07-05T06:52:13Z"},{"alias_kind":"pith_short_16","alias_value":"EMU6PAKHDVH2KTEN","created_at":"2026-07-05T06:52:13Z"},{"alias_kind":"pith_short_8","alias_value":"EMU6PAKH","created_at":"2026-07-05T06:52:13Z"}],"graph_snapshots":[{"event_id":"sha256:0a56c3670e0c445ef1a5172e2be8da370a383a67c70dd634926777377a328225","target":"graph","created_at":"2026-07-05T06:52:13Z","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/2309.10537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in audio generation have been spurred by the evolution of large-scale deep learning models and expansive datasets. However, the task of video-to-audio (V2A) generation continues to be a challenge, principally because of the intricate relationship between the high-dimensional visual and auditory data, and the challenges associated with temporal synchronization. In this study, we introduce FoleyGen, an open-domain V2A generation system built on a language modeling paradigm. FoleyGen leverages an off-the-shelf neural audio codec for bidirectional conversion between waveforms a","authors_text":"Ernie Chang, Gael Le Lan, Varun Nagaraja, Vikas Chandra, Xinhao Mei, Yangyang Shi, Zhaoheng Ni","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T11:33:43Z","title":"FoleyGen: Visually-Guided Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10537","kind":"arxiv","version":1},"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:a6e4924880bc867b148aaa8cbb31c480e71dbe342efeaff3aa397ee0401d0ad9","target":"record","created_at":"2026-07-05T06:52:13Z","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":"a36985d69839c448f5cc82ec70ae6194a5f735d2f672e5882a4696d97281ce3b","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T11:33:43Z","title_canon_sha256":"f908c71bfc7e365e8945bd64dc80bb7ecadb2b6dadde30a6670f4a7c568f0682"},"schema_version":"1.0","source":{"id":"2309.10537","kind":"arxiv","version":1}},"canonical_sha256":"2329e781471d4fa54c8db93d4f196fdbcc40ad45f62e9ba4340110142583f4a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2329e781471d4fa54c8db93d4f196fdbcc40ad45f62e9ba4340110142583f4a2","first_computed_at":"2026-07-05T06:52:13.487744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:13.487744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DoII/XLiTGCOyyNLexzqZ37u6zVQr5szYnrz+hnIma8GHbSETZt0sPddcahGqd1XyZaZXjx/VyvieTpY0i4MCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:13.488275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10537","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6e4924880bc867b148aaa8cbb31c480e71dbe342efeaff3aa397ee0401d0ad9","sha256:0a56c3670e0c445ef1a5172e2be8da370a383a67c70dd634926777377a328225"],"state_sha256":"75e2aa95dd2d80d8259a1ffadd43f35ae65670ab4ac940329b79ba40ffda6987"}