{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RGXQYYSFPHLGHJUYA3BRRVUTB5","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":"f0e89cf9fce73c037479a893b6749283096dcdf07bd48472dff49ca1970d57df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T22:44:36Z","title_canon_sha256":"fa9a1c601d1944714c4f4acf44b9d9f0cbfb2f1c1c6bf3483d7e23cac7bb8aef"},"schema_version":"1.0","source":{"id":"2508.03955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03955","created_at":"2026-07-05T11:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03955v1","created_at":"2026-07-05T11:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03955","created_at":"2026-07-05T11:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"RGXQYYSFPHLG","created_at":"2026-07-05T11:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"RGXQYYSFPHLGHJUY","created_at":"2026-07-05T11:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"RGXQYYSF","created_at":"2026-07-05T11:49:18Z"}],"graph_snapshots":[{"event_id":"sha256:4d838b659e141a3904b4fdf4a93330e385c9edc4520cab2dd017dbe8afcf9b83","target":"graph","created_at":"2026-07-05T11:49:18Z","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/2508.03955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T22:44:36Z","title":"Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03955","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:a26f8ba3aa46efbad9b4f5ada5e563a130f75c125346cb75fe1998338cf8e0b9","target":"record","created_at":"2026-07-05T11:49:18Z","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":"f0e89cf9fce73c037479a893b6749283096dcdf07bd48472dff49ca1970d57df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T22:44:36Z","title_canon_sha256":"fa9a1c601d1944714c4f4acf44b9d9f0cbfb2f1c1c6bf3483d7e23cac7bb8aef"},"schema_version":"1.0","source":{"id":"2508.03955","kind":"arxiv","version":1}},"canonical_sha256":"89af0c624579d663a69806c318d6930f62984da5b49b8778f8388ccb63f817c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89af0c624579d663a69806c318d6930f62984da5b49b8778f8388ccb63f817c1","first_computed_at":"2026-07-05T11:49:18.097716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:18.097716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"33xZ8HemmaC7LoEGEPNBtSVzzh4tUbf5FojsLxywgTPMsWagnk2JovR1HfBIz7MywgqikxfYgv0B7tamGmPLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:18.098168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26f8ba3aa46efbad9b4f5ada5e563a130f75c125346cb75fe1998338cf8e0b9","sha256:4d838b659e141a3904b4fdf4a93330e385c9edc4520cab2dd017dbe8afcf9b83"],"state_sha256":"213c3c0137f102f2ac058aef7cb4e42ab8de40cb3415ac6750301c4358d06969"}