{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EMU6PAKHDVH2KTENXE6U6GLP3P","short_pith_number":"pith:EMU6PAKH","schema_version":"1.0","canonical_sha256":"2329e781471d4fa54c8db93d4f196fdbcc40ad45f62e9ba4340110142583f4a2","source":{"kind":"arxiv","id":"2309.10537","version":1},"attestation_state":"computed","paper":{"title":"FoleyGen: Visually-Guided Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ernie Chang, Gael Le Lan, Varun Nagaraja, Vikas Chandra, Xinhao Mei, Yangyang Shi, Zhaoheng Ni","submitted_at":"2023-09-19T11:33:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.10537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-19T11:33:43Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"f908c71bfc7e365e8945bd64dc80bb7ecadb2b6dadde30a6670f4a7c568f0682","abstract_canon_sha256":"a36985d69839c448f5cc82ec70ae6194a5f735d2f672e5882a4696d97281ce3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:13.488275Z","signature_b64":"DoII/XLiTGCOyyNLexzqZ37u6zVQr5szYnrz+hnIma8GHbSETZt0sPddcahGqd1XyZaZXjx/VyvieTpY0i4MCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2329e781471d4fa54c8db93d4f196fdbcc40ad45f62e9ba4340110142583f4a2","last_reissued_at":"2026-07-05T06:52:13.487744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:13.487744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoleyGen: Visually-Guided Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ernie Chang, Gael Le Lan, Varun Nagaraja, Vikas Chandra, Xinhao Mei, Yangyang Shi, Zhaoheng Ni","submitted_at":"2023-09-19T11:33:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10537","kind":"arxiv","version":1},"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/2309.10537/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.10537","created_at":"2026-07-05T06:52:13.487814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10537v1","created_at":"2026-07-05T06:52:13.487814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10537","created_at":"2026-07-05T06:52:13.487814+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMU6PAKHDVH2","created_at":"2026-07-05T06:52:13.487814+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMU6PAKHDVH2KTEN","created_at":"2026-07-05T06:52:13.487814+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMU6PAKH","created_at":"2026-07-05T06:52:13.487814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P","json":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P.json","graph_json":"https://pith.science/api/pith-number/EMU6PAKHDVH2KTENXE6U6GLP3P/graph.json","events_json":"https://pith.science/api/pith-number/EMU6PAKHDVH2KTENXE6U6GLP3P/events.json","paper":"https://pith.science/paper/EMU6PAKH"},"agent_actions":{"view_html":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P","download_json":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P.json","view_paper":"https://pith.science/paper/EMU6PAKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10537&json=true","fetch_graph":"https://pith.science/api/pith-number/EMU6PAKHDVH2KTENXE6U6GLP3P/graph.json","fetch_events":"https://pith.science/api/pith-number/EMU6PAKHDVH2KTENXE6U6GLP3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P/action/storage_attestation","attest_author":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P/action/author_attestation","sign_citation":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P/action/citation_signature","submit_replication":"https://pith.science/pith/EMU6PAKHDVH2KTENXE6U6GLP3P/action/replication_record"}},"created_at":"2026-07-05T06:52:13.487814+00:00","updated_at":"2026-07-05T06:52:13.487814+00:00"}