{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VDCL3KMKZI6WHSDZVWPGPDIA54","short_pith_number":"pith:VDCL3KMK","schema_version":"1.0","canonical_sha256":"a8c4bda98aca3d63c879ad9e678d00ef0058f3ba3099b410421915950d2daa23","source":{"kind":"arxiv","id":"2305.04001","version":2},"attestation_state":"computed","paper":{"title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaerin Kong, Donghyeon Jeon, Nojun Kwak, Seungwoo Lee","submitted_at":"2023-05-06T10:26:56Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.04001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T10:26:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"add7432f6a90c0edb15771f1ec4c502ce1d40b020ff988648ec316b6edc07489","abstract_canon_sha256":"ff6af187bb91e007f57be60b08543f6e7fdab663c46168585624d371da9578e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:49.092007Z","signature_b64":"e0kz1Ydxxw50sydo2EPuXX2HaVRzWUmprZCEWiD9NrOV+E7UpyINW3eh9pB1JwGJ6nc2nziS/rjYSZb24FchAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8c4bda98aca3d63c879ad9e678d00ef0058f3ba3099b410421915950d2daa23","last_reissued_at":"2026-07-05T06:12:49.091534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:49.091534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaerin Kong, Donghyeon Jeon, Nojun Kwak, Seungwoo Lee","submitted_at":"2023-05-06T10:26:56Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04001","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.04001/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.04001","created_at":"2026-07-05T06:12:49.091591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04001v2","created_at":"2026-07-05T06:12:49.091591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04001","created_at":"2026-07-05T06:12:49.091591+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDCL3KMKZI6W","created_at":"2026-07-05T06:12:49.091591+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDCL3KMKZI6WHSDZ","created_at":"2026-07-05T06:12:49.091591+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDCL3KMK","created_at":"2026-07-05T06:12:49.091591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54","json":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54.json","graph_json":"https://pith.science/api/pith-number/VDCL3KMKZI6WHSDZVWPGPDIA54/graph.json","events_json":"https://pith.science/api/pith-number/VDCL3KMKZI6WHSDZVWPGPDIA54/events.json","paper":"https://pith.science/paper/VDCL3KMK"},"agent_actions":{"view_html":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54","download_json":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54.json","view_paper":"https://pith.science/paper/VDCL3KMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04001&json=true","fetch_graph":"https://pith.science/api/pith-number/VDCL3KMKZI6WHSDZVWPGPDIA54/graph.json","fetch_events":"https://pith.science/api/pith-number/VDCL3KMKZI6WHSDZVWPGPDIA54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54/action/storage_attestation","attest_author":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54/action/author_attestation","sign_citation":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54/action/citation_signature","submit_replication":"https://pith.science/pith/VDCL3KMKZI6WHSDZVWPGPDIA54/action/replication_record"}},"created_at":"2026-07-05T06:12:49.091591+00:00","updated_at":"2026-07-05T06:12:49.091591+00:00"}