{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3HIUAJLZMNMKZLGXQZ6LSNCP2G","short_pith_number":"pith:3HIUAJLZ","canonical_record":{"source":{"id":"2412.18157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-24T04:29:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"af329d0849123a7bdfaf404b98c1f31babac76e27f69ab78f8e52c15293f3bb8","abstract_canon_sha256":"0e537cd7aeecd9d1e428c745d95dd197f54707d99279e0e20727aaa5f71fe756"},"schema_version":"1.0"},"canonical_sha256":"d9d14025796358acacd7867cb9344fd187aa06c749211823d4e0a4e49df8624c","source":{"kind":"arxiv","id":"2412.18157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18157","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18157v1","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18157","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"3HIUAJLZMNMK","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"pith_short_16","alias_value":"3HIUAJLZMNMKZLGX","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"pith_short_8","alias_value":"3HIUAJLZ","created_at":"2026-07-05T09:53:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3HIUAJLZMNMKZLGXQZ6LSNCP2G","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-24T04:29:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"af329d0849123a7bdfaf404b98c1f31babac76e27f69ab78f8e52c15293f3bb8","abstract_canon_sha256":"0e537cd7aeecd9d1e428c745d95dd197f54707d99279e0e20727aaa5f71fe756"},"schema_version":"1.0"},"canonical_sha256":"d9d14025796358acacd7867cb9344fd187aa06c749211823d4e0a4e49df8624c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:50.790228Z","signature_b64":"WsJ9S7g+H5cNwrg4ndMEfekvksf+4qdytYNcIDMA5q8vj6wmCy69ZCdf/BI9MC4DBzxgkNNXkfmQ9zUNSOaHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9d14025796358acacd7867cb9344fd187aa06c749211823d4e0a4e49df8624c","last_reissued_at":"2026-07-05T09:53:50.789766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:50.789766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18157","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/Ejm8LfrlY5W6+3UlmeT2H4oNqXFk4ww1sngCOOGUBZtlvmXCEYNQUvvzBmTgbCIk5fSkRVK8M1T/XmeyUMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:36:03.029916Z"},"content_sha256":"e9be21bc901c60070724bf83611f04d30beb558a4dd222f266f6b17f69ecf3b1","schema_version":"1.0","event_id":"sha256:e9be21bc901c60070724bf83611f04d30beb558a4dd222f266f6b17f69ecf3b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3HIUAJLZMNMKZLGXQZ6LSNCP2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mengyue Wu, Xuenan Xu, Yaoyun Zhang","submitted_at":"2024-12-24T04:29:46Z","abstract_excerpt":"The video-to-audio (V2A) generation task has drawn attention in the field of multimedia due to the practicality in producing Foley sound. Semantic and temporal conditions are fed to the generation model to indicate sound events and temporal occurrence. Recent studies on synthesizing immersive and synchronized audio are faced with challenges on videos with moving visual presence. The temporal condition is not accurate enough while low-resolution semantic condition exacerbates the problem. To tackle these challenges, we propose Smooth-Foley, a V2A generative model taking semantic guidance from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18157","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/2412.18157/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":"2026-07-05T09:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlqbRi0psBMYdrqze2Lmgyik61rjzLoy3uXL/wvb6u4cI3Y3eC3Fa+x80LbogweAtPLnv6dz0OVjBkYSqHyWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:36:03.030497Z"},"content_sha256":"627b9113dc4e28b21ae47fd9ac7d2fb4922b0c7fe9303fbb6e8f491078bb8f0b","schema_version":"1.0","event_id":"sha256:627b9113dc4e28b21ae47fd9ac7d2fb4922b0c7fe9303fbb6e8f491078bb8f0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G/bundle.json","state_url":"https://pith.science/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G/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":"2026-08-19T21:36:03Z","links":{"resolver":"https://pith.science/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G","bundle":"https://pith.science/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G/bundle.json","state":"https://pith.science/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HIUAJLZMNMKZLGXQZ6LSNCP2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3HIUAJLZMNMKZLGXQZ6LSNCP2G","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":"0e537cd7aeecd9d1e428c745d95dd197f54707d99279e0e20727aaa5f71fe756","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-24T04:29:46Z","title_canon_sha256":"af329d0849123a7bdfaf404b98c1f31babac76e27f69ab78f8e52c15293f3bb8"},"schema_version":"1.0","source":{"id":"2412.18157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18157","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18157v1","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18157","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"3HIUAJLZMNMK","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"pith_short_16","alias_value":"3HIUAJLZMNMKZLGX","created_at":"2026-07-05T09:53:50Z"},{"alias_kind":"pith_short_8","alias_value":"3HIUAJLZ","created_at":"2026-07-05T09:53:50Z"}],"graph_snapshots":[{"event_id":"sha256:627b9113dc4e28b21ae47fd9ac7d2fb4922b0c7fe9303fbb6e8f491078bb8f0b","target":"graph","created_at":"2026-07-05T09:53:50Z","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/2412.18157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The video-to-audio (V2A) generation task has drawn attention in the field of multimedia due to the practicality in producing Foley sound. Semantic and temporal conditions are fed to the generation model to indicate sound events and temporal occurrence. Recent studies on synthesizing immersive and synchronized audio are faced with challenges on videos with moving visual presence. The temporal condition is not accurate enough while low-resolution semantic condition exacerbates the problem. To tackle these challenges, we propose Smooth-Foley, a V2A generative model taking semantic guidance from t","authors_text":"Mengyue Wu, Xuenan Xu, Yaoyun Zhang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-24T04:29:46Z","title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18157","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:e9be21bc901c60070724bf83611f04d30beb558a4dd222f266f6b17f69ecf3b1","target":"record","created_at":"2026-07-05T09:53:50Z","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":"0e537cd7aeecd9d1e428c745d95dd197f54707d99279e0e20727aaa5f71fe756","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-24T04:29:46Z","title_canon_sha256":"af329d0849123a7bdfaf404b98c1f31babac76e27f69ab78f8e52c15293f3bb8"},"schema_version":"1.0","source":{"id":"2412.18157","kind":"arxiv","version":1}},"canonical_sha256":"d9d14025796358acacd7867cb9344fd187aa06c749211823d4e0a4e49df8624c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9d14025796358acacd7867cb9344fd187aa06c749211823d4e0a4e49df8624c","first_computed_at":"2026-07-05T09:53:50.789766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:50.789766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WsJ9S7g+H5cNwrg4ndMEfekvksf+4qdytYNcIDMA5q8vj6wmCy69ZCdf/BI9MC4DBzxgkNNXkfmQ9zUNSOaHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:50.790228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9be21bc901c60070724bf83611f04d30beb558a4dd222f266f6b17f69ecf3b1","sha256:627b9113dc4e28b21ae47fd9ac7d2fb4922b0c7fe9303fbb6e8f491078bb8f0b"],"state_sha256":"dbd33a8895a49363c7780e4fb90c72030fea52b8b3bc2abc04c8be4383198779"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIHbL3U0BiAPUSkamiaS6FD6Xivbv6AwI2p8X4rU13YdyqWyz3Ivp77DiqA3UUl4//SXjeNyg6yEFHW/B5HLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:36:03.034655Z","bundle_sha256":"886844486c8e2217c685b6841c6c3544a866ff836aa29c8b990b214d24f46099"}}