{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OTKAL72KX3INXIK2VOWPDM5FE6","short_pith_number":"pith:OTKAL72K","schema_version":"1.0","canonical_sha256":"74d405ff4abed0dba15aabacf1b3a52790cf4c129e1ef84830e11091360b9ed4","source":{"kind":"arxiv","id":"2411.17698","version":4},"attestation_state":"computed","paper":{"title":"Video-Guided Foley Sound Generation with Multimodal Controls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Bryan Russell, David Bourgin, Justin Salamon, Oriol Nieto, Prem Seetharaman, Ziyang Chen","submitted_at":"2024-11-26T18:59:58Z","abstract_excerpt":"Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To address this problem, we introduce MultiFoley, a model designed for video-guided sound generation that supports multimodal conditioning through text, audio, and video. Given a silent video and a text prompt, MultiFoley allows users to create clean sounds (e.g., skateboard wheels spinning without wind noise) or more whimsical sounds (e.g., making a lion's roar sound like a cat's meow). MultiFoley also allows users to ch"},"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":"2411.17698","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:59:58Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"8b333103eefe5a35f1bba2b703c8a5d76c3279bb8c1dfc0e04070f79181f7542","abstract_canon_sha256":"0e153af573c73416d5ed35ccb5f512356869cbf8c6e7acdd12ebfbcba533ba00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:34.409008Z","signature_b64":"CfJw48u1wKTwYODm4Qg4OTbZIrKedLxe+FYaZMXp15M+dWI1rcy+ccpwKuZ8EX3IsM6M8hW9ppMXjo8QRGyYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d405ff4abed0dba15aabacf1b3a52790cf4c129e1ef84830e11091360b9ed4","last_reissued_at":"2026-07-05T10:32:34.408493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:34.408493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Guided Foley Sound Generation with Multimodal Controls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Bryan Russell, David Bourgin, Justin Salamon, Oriol Nieto, Prem Seetharaman, Ziyang Chen","submitted_at":"2024-11-26T18:59:58Z","abstract_excerpt":"Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To address this problem, we introduce MultiFoley, a model designed for video-guided sound generation that supports multimodal conditioning through text, audio, and video. Given a silent video and a text prompt, MultiFoley allows users to create clean sounds (e.g., skateboard wheels spinning without wind noise) or more whimsical sounds (e.g., making a lion's roar sound like a cat's meow). MultiFoley also allows users to ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17698","kind":"arxiv","version":4},"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/2411.17698/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":"2411.17698","created_at":"2026-07-05T10:32:34.408554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17698v4","created_at":"2026-07-05T10:32:34.408554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17698","created_at":"2026-07-05T10:32:34.408554+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTKAL72KX3IN","created_at":"2026-07-05T10:32:34.408554+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTKAL72KX3INXIK2","created_at":"2026-07-05T10:32:34.408554+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTKAL72K","created_at":"2026-07-05T10:32:34.408554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12555","citing_title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6","json":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6.json","graph_json":"https://pith.science/api/pith-number/OTKAL72KX3INXIK2VOWPDM5FE6/graph.json","events_json":"https://pith.science/api/pith-number/OTKAL72KX3INXIK2VOWPDM5FE6/events.json","paper":"https://pith.science/paper/OTKAL72K"},"agent_actions":{"view_html":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6","download_json":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6.json","view_paper":"https://pith.science/paper/OTKAL72K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17698&json=true","fetch_graph":"https://pith.science/api/pith-number/OTKAL72KX3INXIK2VOWPDM5FE6/graph.json","fetch_events":"https://pith.science/api/pith-number/OTKAL72KX3INXIK2VOWPDM5FE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/action/storage_attestation","attest_author":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/action/author_attestation","sign_citation":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/action/citation_signature","submit_replication":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/action/replication_record"}},"created_at":"2026-07-05T10:32:34.408554+00:00","updated_at":"2026-07-05T10:32:34.408554+00:00"}