{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HTF4WOLN3H4WAQJ6X4X2WGGHGU","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":"afd260751972c41a544f223760fdff35387313fc36db331e2e30de569636aefb","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:36:10Z","title_canon_sha256":"5f29f4a43eecf02e3ee545c74ea75ffa021a0a520c657d2b1fb4897cd0362d39"},"schema_version":"1.0","source":{"id":"2412.10768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10768","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10768v1","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10768","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"HTF4WOLN3H4W","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"HTF4WOLN3H4WAQJ6","created_at":"2026-07-05T09:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"HTF4WOLN","created_at":"2026-07-05T09:49:21Z"}],"graph_snapshots":[{"event_id":"sha256:d3b23071d7a481c1f48383f3c20b0e5b46ff7df9de452208f451ab099a04c0d6","target":"graph","created_at":"2026-07-05T09:49:21Z","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/2412.10768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous appr","authors_text":"Saksham Singh Kushwaha, Yapeng Tian","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:36:10Z","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10768","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":"sha256:84b97ae7b0f108b2916ad74a82e51728e64fd703d50f7b3fa6a130a51f499b6d","target":"record","created_at":"2026-07-05T09:49:21Z","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":"afd260751972c41a544f223760fdff35387313fc36db331e2e30de569636aefb","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T09:36:10Z","title_canon_sha256":"5f29f4a43eecf02e3ee545c74ea75ffa021a0a520c657d2b1fb4897cd0362d39"},"schema_version":"1.0","source":{"id":"2412.10768","kind":"arxiv","version":1}},"canonical_sha256":"3ccbcb396dd9f960413ebf2fab18c735127e999c64c7b24a7d0964638e897de7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ccbcb396dd9f960413ebf2fab18c735127e999c64c7b24a7d0964638e897de7","first_computed_at":"2026-07-05T09:49:21.957005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:21.957005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KCbIwXtz1q3vqHngEfreMPJr0iENZcynF1iCMLeUJpWTX3/DaZJJxHQl1ytOE5ZLrd3xlEPxWZS44IiW/TpsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:21.957384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84b97ae7b0f108b2916ad74a82e51728e64fd703d50f7b3fa6a130a51f499b6d","sha256:d3b23071d7a481c1f48383f3c20b0e5b46ff7df9de452208f451ab099a04c0d6"],"state_sha256":"04430730c68834f183ed18aee3bd6fc95885f460c15307f9bc0b47d514b6b94a"}