{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2HQFOKEXOAICOOUIWW2EPDDE67","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":"209e1ac2b670f92235eb4c95bf291f70da0aad38a5beba744eb49bcc05fe68a6","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T17:59:01Z","title_canon_sha256":"045f2c22d6e572993c2423ec4932a666143748ccedd5b89e20dc584b623d28b8"},"schema_version":"1.0","source":{"id":"2409.13689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13689","created_at":"2026-07-05T09:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13689v1","created_at":"2026-07-05T09:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13689","created_at":"2026-07-05T09:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"2HQFOKEXOAIC","created_at":"2026-07-05T09:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"2HQFOKEXOAICOOUI","created_at":"2026-07-05T09:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"2HQFOKEX","created_at":"2026-07-05T09:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:87e642053c0001014e71dfb76ff2a802af37f2cfa1583c33c7667f138a077f10","target":"graph","created_at":"2026-07-05T09:09:47Z","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/2409.13689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce V-AURA, the first autoregressive model to achieve high temporal alignment and relevance in video-to-audio generation. V-AURA uses a high-framerate visual feature extractor and a cross-modal audio-visual feature fusion strategy to capture fine-grained visual motion events and ensure precise temporal alignment. Additionally, we propose VisualSound, a benchmark dataset with high audio-visual relevance. VisualSound is based on VGGSound, a video dataset consisting of in-the-wild samples extracted from YouTube. During the curation, we remove samples where auditory events are not aligned","authors_text":"Esa Rahtu, Ilpo Viertola, Vladimir Iashin","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T17:59:01Z","title":"Temporally Aligned Audio for Video with Autoregression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13689","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:e07bac3f1b6a20f28011b9d9417465fff2c810ebdcf53eae2d5564ea65dbae69","target":"record","created_at":"2026-07-05T09:09:47Z","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":"209e1ac2b670f92235eb4c95bf291f70da0aad38a5beba744eb49bcc05fe68a6","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T17:59:01Z","title_canon_sha256":"045f2c22d6e572993c2423ec4932a666143748ccedd5b89e20dc584b623d28b8"},"schema_version":"1.0","source":{"id":"2409.13689","kind":"arxiv","version":1}},"canonical_sha256":"d1e05728977010273a88b5b4478c64f7c3c6cc6e91caf53ffe6fa30b874f247a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1e05728977010273a88b5b4478c64f7c3c6cc6e91caf53ffe6fa30b874f247a","first_computed_at":"2026-07-05T09:09:47.383671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:47.383671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eEjmgMUDPGSl8m9UyOJuhiZCqoyUbFZefHONLVKnFmXWN6ADGRmjLs9hv16UPKeVyHa4RST09mYeWqlmjT+rAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:47.384206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e07bac3f1b6a20f28011b9d9417465fff2c810ebdcf53eae2d5564ea65dbae69","sha256:87e642053c0001014e71dfb76ff2a802af37f2cfa1583c33c7667f138a077f10"],"state_sha256":"64dab880f7e9c0213ebdcb080144ba81a786548001bd521667f8700ed61fbcdc"}