{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VDCL3KMKZI6WHSDZVWPGPDIA54","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":"ff6af187bb91e007f57be60b08543f6e7fdab663c46168585624d371da9578e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T10:26:56Z","title_canon_sha256":"add7432f6a90c0edb15771f1ec4c502ce1d40b020ff988648ec316b6edc07489"},"schema_version":"1.0","source":{"id":"2305.04001","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04001","created_at":"2026-07-05T06:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04001v2","created_at":"2026-07-05T06:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04001","created_at":"2026-07-05T06:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"VDCL3KMKZI6W","created_at":"2026-07-05T06:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"VDCL3KMKZI6WHSDZ","created_at":"2026-07-05T06:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"VDCL3KMK","created_at":"2026-07-05T06:12:49Z"}],"graph_snapshots":[{"event_id":"sha256:a9aaf4709b54fd41176b4edb622522c6693892f0f83340e57453d0a07cb17075","target":"graph","created_at":"2026-07-05T06:12:49Z","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/2305.04001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in diffusion models have showcased promising results in the text-to-video (T2V) synthesis task. However, as these T2V models solely employ text as the guidance, they tend to struggle in modeling detailed temporal dynamics. In this paper, we introduce a novel T2V framework that additionally employ audio signals to control the temporal dynamics, empowering an off-the-shelf T2I diffusion to generate audio-aligned videos. We propose audio-based regional editing and signal smoothing to strike a good balance between the two contradicting desiderata of video synthesis, i.e., temporal ","authors_text":"Chaerin Kong, Donghyeon Jeon, Nojun Kwak, Seungwoo Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T10:26:56Z","title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04001","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:e657c0bde02e4f811d0930b44e906f7a6ecf858d583e94d020996bd915e73f80","target":"record","created_at":"2026-07-05T06:12:49Z","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":"ff6af187bb91e007f57be60b08543f6e7fdab663c46168585624d371da9578e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T10:26:56Z","title_canon_sha256":"add7432f6a90c0edb15771f1ec4c502ce1d40b020ff988648ec316b6edc07489"},"schema_version":"1.0","source":{"id":"2305.04001","kind":"arxiv","version":2}},"canonical_sha256":"a8c4bda98aca3d63c879ad9e678d00ef0058f3ba3099b410421915950d2daa23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8c4bda98aca3d63c879ad9e678d00ef0058f3ba3099b410421915950d2daa23","first_computed_at":"2026-07-05T06:12:49.091534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:49.091534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e0kz1Ydxxw50sydo2EPuXX2HaVRzWUmprZCEWiD9NrOV+E7UpyINW3eh9pB1JwGJ6nc2nziS/rjYSZb24FchAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:49.092007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.04001","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e657c0bde02e4f811d0930b44e906f7a6ecf858d583e94d020996bd915e73f80","sha256:a9aaf4709b54fd41176b4edb622522c6693892f0f83340e57453d0a07cb17075"],"state_sha256":"037675f1ebd1d25dc79582c88a70758c0795af698ce20184368d4548773d8747"}