{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OTKAL72KX3INXIK2VOWPDM5FE6","short_pith_number":"pith:OTKAL72K","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"},"canonical_sha256":"74d405ff4abed0dba15aabacf1b3a52790cf4c129e1ef84830e11091360b9ed4","source":{"kind":"arxiv","id":"2411.17698","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17698","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17698v4","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17698","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"pith_short_12","alias_value":"OTKAL72KX3IN","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"pith_short_16","alias_value":"OTKAL72KX3INXIK2","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"pith_short_8","alias_value":"OTKAL72K","created_at":"2026-07-05T10:32:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OTKAL72KX3INXIK2VOWPDM5FE6","target":"record","payload":{"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"},"canonical_sha256":"74d405ff4abed0dba15aabacf1b3a52790cf4c129e1ef84830e11091360b9ed4","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"},"source_kind":"arxiv","source_id":"2411.17698","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hc6QUHnJMc8/D7Z5KyptPXVThfr7lY/ldMcXCIQzBmuDdPnwHNKk3V+nCkoq7NAuMrijm+E0u4r4Fzv+nyn2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:05:31.284161Z"},"content_sha256":"8d3be961678233415af30d688a46c2a8dc44782806445ce4d4a52d4eed8e77d9","schema_version":"1.0","event_id":"sha256:8d3be961678233415af30d688a46c2a8dc44782806445ce4d4a52d4eed8e77d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OTKAL72KX3INXIK2VOWPDM5FE6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SvrPR2ZbKFtT9d/orVqSpAJoUaRHbBT9thitfT9qvK/d3TOT7w4EDfkFoeMXphA0gSzCVDHId2h+h1+Mk6b/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:05:31.284674Z"},"content_sha256":"41496d3cd177d97d26a621f2921cd32861f368c5b147c0adddf0d6aecebe1a3e","schema_version":"1.0","event_id":"sha256:41496d3cd177d97d26a621f2921cd32861f368c5b147c0adddf0d6aecebe1a3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/bundle.json","state_url":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTKAL72KX3INXIK2VOWPDM5FE6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T20:05:31Z","links":{"resolver":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6","bundle":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/bundle.json","state":"https://pith.science/pith/OTKAL72KX3INXIK2VOWPDM5FE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTKAL72KX3INXIK2VOWPDM5FE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OTKAL72KX3INXIK2VOWPDM5FE6","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":"0e153af573c73416d5ed35ccb5f512356869cbf8c6e7acdd12ebfbcba533ba00","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:59:58Z","title_canon_sha256":"8b333103eefe5a35f1bba2b703c8a5d76c3279bb8c1dfc0e04070f79181f7542"},"schema_version":"1.0","source":{"id":"2411.17698","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17698","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17698v4","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17698","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"pith_short_12","alias_value":"OTKAL72KX3IN","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"pith_short_16","alias_value":"OTKAL72KX3INXIK2","created_at":"2026-07-05T10:32:34Z"},{"alias_kind":"pith_short_8","alias_value":"OTKAL72K","created_at":"2026-07-05T10:32:34Z"}],"graph_snapshots":[{"event_id":"sha256:41496d3cd177d97d26a621f2921cd32861f368c5b147c0adddf0d6aecebe1a3e","target":"graph","created_at":"2026-07-05T10:32:34Z","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/2411.17698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrew Owens, Bryan Russell, David Bourgin, Justin Salamon, Oriol Nieto, Prem Seetharaman, Ziyang Chen","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:59:58Z","title":"Video-Guided Foley Sound Generation with Multimodal Controls"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17698","kind":"arxiv","version":4},"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":"sha256:8d3be961678233415af30d688a46c2a8dc44782806445ce4d4a52d4eed8e77d9","target":"record","created_at":"2026-07-05T10:32:34Z","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":"0e153af573c73416d5ed35ccb5f512356869cbf8c6e7acdd12ebfbcba533ba00","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:59:58Z","title_canon_sha256":"8b333103eefe5a35f1bba2b703c8a5d76c3279bb8c1dfc0e04070f79181f7542"},"schema_version":"1.0","source":{"id":"2411.17698","kind":"arxiv","version":4}},"canonical_sha256":"74d405ff4abed0dba15aabacf1b3a52790cf4c129e1ef84830e11091360b9ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74d405ff4abed0dba15aabacf1b3a52790cf4c129e1ef84830e11091360b9ed4","first_computed_at":"2026-07-05T10:32:34.408493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:34.408493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CfJw48u1wKTwYODm4Qg4OTbZIrKedLxe+FYaZMXp15M+dWI1rcy+ccpwKuZ8EX3IsM6M8hW9ppMXjo8QRGyYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:34.409008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17698","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d3be961678233415af30d688a46c2a8dc44782806445ce4d4a52d4eed8e77d9","sha256:41496d3cd177d97d26a621f2921cd32861f368c5b147c0adddf0d6aecebe1a3e"],"state_sha256":"3db21718f3a6412acff791e8be8303f5a5f8600bde36215f26a0b74242c8b26a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6UDm3waUmcseB8+684NlAokie5I/JYh0vlirEL+qOFgCarKEf7PPXq/JxXUKVPpyNBLWFN6rJ8b40LTisxXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:05:31.289961Z","bundle_sha256":"cfd108ef95a81f3e8888fc91982dcdcf7b6c4838cc63b68724a7c29606f8c2f4"}}