{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WUP76UNY7GTTKOP3RSKMTH6DVK","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":"566a91dc98bad7050d131a3c74b2d7ad6a483fed30e9f9e2e6c13082d37ceb60","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-13T08:33:03Z","title_canon_sha256":"cd8af3ff0c91a5c26510dd593293e3d40947a648a396915dec33c2ec0daed437"},"schema_version":"1.0","source":{"id":"2409.08628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08628","created_at":"2026-07-05T09:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08628v1","created_at":"2026-07-05T09:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08628","created_at":"2026-07-05T09:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"WUP76UNY7GTT","created_at":"2026-07-05T09:06:44Z"},{"alias_kind":"pith_short_16","alias_value":"WUP76UNY7GTTKOP3","created_at":"2026-07-05T09:06:44Z"},{"alias_kind":"pith_short_8","alias_value":"WUP76UNY","created_at":"2026-07-05T09:06:44Z"}],"graph_snapshots":[{"event_id":"sha256:77491dfaebd997345877749d0407879b0ee6f55085c8e0baf9357e92b795e2c8","target":"graph","created_at":"2026-07-05T09:06:44Z","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/2409.08628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our research introduces an innovative framework for video-to-audio synthesis, which solves the problems of audio-video desynchronization and semantic loss in the audio. By incorporating a semantic alignment adapter and a temporal synchronization adapter, our method significantly improves semantic integrity and the precision of beat point synchronization, particularly in fast-paced action sequences. Utilizing a contrastive audio-visual pre-trained encoder, our model is trained with video and high-quality audio data, improving the quality of the generated audio. This dual-adapter approach empowe","authors_text":"Dan Luo, Huan Liao, Jun Wang, Zhiheng Li, Zhiqi Huang, Zhiyong Wu","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-13T08:33:03Z","title":"Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08628","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":"sha256:6ee55c9612453cae1212abaddd2db6df18d5dc391728e422f441d82375ef82b7","target":"record","created_at":"2026-07-05T09:06:44Z","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":"566a91dc98bad7050d131a3c74b2d7ad6a483fed30e9f9e2e6c13082d37ceb60","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-13T08:33:03Z","title_canon_sha256":"cd8af3ff0c91a5c26510dd593293e3d40947a648a396915dec33c2ec0daed437"},"schema_version":"1.0","source":{"id":"2409.08628","kind":"arxiv","version":1}},"canonical_sha256":"b51fff51b8f9a73539fb8c94c99fc3aa8579135c7172d5289aec33b2d36aec68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b51fff51b8f9a73539fb8c94c99fc3aa8579135c7172d5289aec33b2d36aec68","first_computed_at":"2026-07-05T09:06:44.657644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:44.657644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JvKE+eLJAqjC7lz2UbFXBcghTvE2WDN+HVEK96JM7rLPOWQpH5n7EqoIn6beWXmZslvdGRjQhzzIVaaBMlTpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:44.658065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ee55c9612453cae1212abaddd2db6df18d5dc391728e422f441d82375ef82b7","sha256:77491dfaebd997345877749d0407879b0ee6f55085c8e0baf9357e92b795e2c8"],"state_sha256":"16eec9d05f1ce2b7883e38113f5b8baefc0583564736c75baf8e57759dfc3248"}