{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RGXQYYSFPHLGHJUYA3BRRVUTB5","short_pith_number":"pith:RGXQYYSF","schema_version":"1.0","canonical_sha256":"89af0c624579d663a69806c318d6930f62984da5b49b8778f8388ccb63f817c1","source":{"kind":"arxiv","id":"2508.03955","version":1},"attestation_state":"computed","paper":{"title":"Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-En Wu, Jinhong Lin, Junjie Hu, Lin Zhang, Pedro Morgado, Ruiyi Zhang, Shentong Mo, Tong Sun, Wen Xiao, Yibing Wei, Yijing Zhang, Yufan Zhou, Zefan Cai","submitted_at":"2025-08-05T22:44:36Z","abstract_excerpt":"Recent advances in audio-synchronized visual animation enable control of video content using audios from specific classes. However, existing methods rely heavily on expensive manual curation of high-quality, class-specific training videos, posing challenges to scaling up to diverse audio-video classes in the open world. In this work, we propose an efficient two-stage training paradigm to scale up audio-synchronized visual animation using abundant but noisy videos. In stage one, we automatically curate large-scale videos for pretraining, allowing the model to learn diverse but imperfect audio-v"},"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":"2508.03955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T22:44:36Z","cross_cats_sorted":[],"title_canon_sha256":"fa9a1c601d1944714c4f4acf44b9d9f0cbfb2f1c1c6bf3483d7e23cac7bb8aef","abstract_canon_sha256":"f0e89cf9fce73c037479a893b6749283096dcdf07bd48472dff49ca1970d57df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:18.098168Z","signature_b64":"33xZ8HemmaC7LoEGEPNBtSVzzh4tUbf5FojsLxywgTPMsWagnk2JovR1HfBIz7MywgqikxfYgv0B7tamGmPLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89af0c624579d663a69806c318d6930f62984da5b49b8778f8388ccb63f817c1","last_reissued_at":"2026-07-05T11:49:18.097716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:18.097716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-En Wu, Jinhong Lin, Junjie Hu, Lin Zhang, Pedro Morgado, Ruiyi Zhang, Shentong Mo, Tong Sun, Wen Xiao, Yibing Wei, Yijing Zhang, Yufan Zhou, Zefan Cai","submitted_at":"2025-08-05T22:44:36Z","abstract_excerpt":"Recent advances in audio-synchronized visual animation enable control of video content using audios from specific classes. However, existing methods rely heavily on expensive manual curation of high-quality, class-specific training videos, posing challenges to scaling up to diverse audio-video classes in the open world. In this work, we propose an efficient two-stage training paradigm to scale up audio-synchronized visual animation using abundant but noisy videos. In stage one, we automatically curate large-scale videos for pretraining, allowing the model to learn diverse but imperfect audio-v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03955","kind":"arxiv","version":1},"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/2508.03955/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":"2508.03955","created_at":"2026-07-05T11:49:18.097782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03955v1","created_at":"2026-07-05T11:49:18.097782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03955","created_at":"2026-07-05T11:49:18.097782+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGXQYYSFPHLG","created_at":"2026-07-05T11:49:18.097782+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGXQYYSFPHLGHJUY","created_at":"2026-07-05T11:49:18.097782+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGXQYYSF","created_at":"2026-07-05T11:49:18.097782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5","json":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5.json","graph_json":"https://pith.science/api/pith-number/RGXQYYSFPHLGHJUYA3BRRVUTB5/graph.json","events_json":"https://pith.science/api/pith-number/RGXQYYSFPHLGHJUYA3BRRVUTB5/events.json","paper":"https://pith.science/paper/RGXQYYSF"},"agent_actions":{"view_html":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5","download_json":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5.json","view_paper":"https://pith.science/paper/RGXQYYSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03955&json=true","fetch_graph":"https://pith.science/api/pith-number/RGXQYYSFPHLGHJUYA3BRRVUTB5/graph.json","fetch_events":"https://pith.science/api/pith-number/RGXQYYSFPHLGHJUYA3BRRVUTB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5/action/storage_attestation","attest_author":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5/action/author_attestation","sign_citation":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5/action/citation_signature","submit_replication":"https://pith.science/pith/RGXQYYSFPHLGHJUYA3BRRVUTB5/action/replication_record"}},"created_at":"2026-07-05T11:49:18.097782+00:00","updated_at":"2026-07-05T11:49:18.097782+00:00"}