{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7W3LTFFRSAMSMQUAX5HL7VU2BH","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":"2cabde5918d68eee03364392655bebe08eae4cbcd2f14357d4f48a09b359daea","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T01:59:17Z","title_canon_sha256":"2bebe7f6f4a6bef39fd52263b9dee3edd7afcaeed4d1849b57acf7383e0549f2"},"schema_version":"1.0","source":{"id":"2407.05551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05551","created_at":"2026-07-05T09:54:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05551v2","created_at":"2026-07-05T09:54:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05551","created_at":"2026-07-05T09:54:27Z"},{"alias_kind":"pith_short_12","alias_value":"7W3LTFFRSAMS","created_at":"2026-07-05T09:54:27Z"},{"alias_kind":"pith_short_16","alias_value":"7W3LTFFRSAMSMQUA","created_at":"2026-07-05T09:54:27Z"},{"alias_kind":"pith_short_8","alias_value":"7W3LTFFR","created_at":"2026-07-05T09:54:27Z"}],"graph_snapshots":[{"event_id":"sha256:5843a92533c85655fe8413ba5670d868892dafe593f50e0d7e1cc1a5ec568cbb","target":"graph","created_at":"2026-07-05T09:54:27Z","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/2407.05551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound synthesis for specific objects within the scene. Conversely, text-to-audio generation methods generate high-quality audio but pose challenges in ensuring comprehensive scene depiction and time-varying control. To tackle these challenges, we propose a novel video-and-text-to-audio generation method, called \\ours, where video serves as a conditional control for a text-to-audio generation model. Especially, our method esti","authors_text":"Jiyoung Lee, Sanghyuk Chun, Yujin Jeong, Yunji Kim","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T01:59:17Z","title":"Read, Watch and Scream! Sound Generation from Text and Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05551","kind":"arxiv","version":2},"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":"sha256:5d67fc024ab24dd2d927a6be352543c1e93e7aa4c2087dd71d3363e8e8e522fc","target":"record","created_at":"2026-07-05T09:54:27Z","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":"2cabde5918d68eee03364392655bebe08eae4cbcd2f14357d4f48a09b359daea","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T01:59:17Z","title_canon_sha256":"2bebe7f6f4a6bef39fd52263b9dee3edd7afcaeed4d1849b57acf7383e0549f2"},"schema_version":"1.0","source":{"id":"2407.05551","kind":"arxiv","version":2}},"canonical_sha256":"fdb6b994b19019264280bf4ebfd69a09f4fdbb2b4304afb1e33b5ca6588f03bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdb6b994b19019264280bf4ebfd69a09f4fdbb2b4304afb1e33b5ca6588f03bd","first_computed_at":"2026-07-05T09:54:27.515748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:27.515748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Sne82YnuwNzKmsKBn+WpL5uY5Rrklmeo7rUE6Pm7aMJMvBUWXnMAL0aUuuWDZcgJ7kU3byL+8zXTWvJxwFxAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:27.516382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d67fc024ab24dd2d927a6be352543c1e93e7aa4c2087dd71d3363e8e8e522fc","sha256:5843a92533c85655fe8413ba5670d868892dafe593f50e0d7e1cc1a5ec568cbb"],"state_sha256":"c98d04a50bab0a0c5c5e55fbc9136a135958e34b1eb25c653a5fbfae2a9cd72a"}