{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3WANAKXMK2WM7RMQQ7HWDPIV7K","short_pith_number":"pith:3WANAKXM","canonical_record":{"source":{"id":"2403.05659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T20:17:34Z","cross_cats_sorted":[],"title_canon_sha256":"db1e4a6cdd2bfa33285aa5a3fcb81a20630a1464124c01c249761ce09273e5b7","abstract_canon_sha256":"b578ab24b9e63d9a5040d0fd0020b9460170a06ed58a42f3123b9b8c001c34c8"},"schema_version":"1.0"},"canonical_sha256":"dd80d02aec56accfc59087cf61bd15fab83cde203c0ece67ef0ec6047f7d9273","source":{"kind":"arxiv","id":"2403.05659","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05659","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05659v2","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05659","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"pith_short_12","alias_value":"3WANAKXMK2WM","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"pith_short_16","alias_value":"3WANAKXMK2WM7RMQ","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"pith_short_8","alias_value":"3WANAKXM","created_at":"2026-07-05T08:45:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3WANAKXMK2WM7RMQQ7HWDPIV7K","target":"record","payload":{"canonical_record":{"source":{"id":"2403.05659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T20:17:34Z","cross_cats_sorted":[],"title_canon_sha256":"db1e4a6cdd2bfa33285aa5a3fcb81a20630a1464124c01c249761ce09273e5b7","abstract_canon_sha256":"b578ab24b9e63d9a5040d0fd0020b9460170a06ed58a42f3123b9b8c001c34c8"},"schema_version":"1.0"},"canonical_sha256":"dd80d02aec56accfc59087cf61bd15fab83cde203c0ece67ef0ec6047f7d9273","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:10.957547Z","signature_b64":"V2aIfyzbrnQNtjB5fTPyr5okPwolQhMJkmTKdH2K64lJm2t0KB0ktrGW18veJIZaPL16T3LmIU9OF0O+X0vmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd80d02aec56accfc59087cf61bd15fab83cde203c0ece67ef0ec6047f7d9273","last_reissued_at":"2026-07-05T08:45:10.957104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:10.957104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.05659","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FwUyhsHUZQo+Hj4VMZoxA0sElcySr1WSMzWrBvVCoaHHw9bEghSybzhs4WyqSHzQQrmnMUTMlyxvfbhHvq2gCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:31:23.099743Z"},"content_sha256":"fe7b9ab94ba6dd0de859b1f85e060981b8979b40de83ad8ee273051f5ca9b797","schema_version":"1.0","event_id":"sha256:fe7b9ab94ba6dd0de859b1f85e060981b8979b40de83ad8ee273051f5ca9b797"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3WANAKXMK2WM7RMQQ7HWDPIV7K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Synchronized Visual Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lin Zhang, Pedro Morgado, Shentong Mo, Yijing Zhang","submitted_at":"2024-03-08T20:17:34Z","abstract_excerpt":"Current visual generation methods can produce high quality videos guided by texts. However, effectively controlling object dynamics remains a challenge. This work explores audio as a cue to generate temporally synchronized image animations. We introduce Audio Synchronized Visual Animation (ASVA), a task animating a static image to demonstrate motion dynamics, temporally guided by audio clips across multiple classes. To this end, we present AVSync15, a dataset curated from VGGSound with videos featuring synchronized audio visual events across 15 categories. We also present a diffusion model, AV"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05659","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/2403.05659/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1fWRqi1sYnRImvg7ggQPUUHEwkkHkEkaE4CbE6h+GEEa+VIjzi/CM0w8idCqPwZ0cpGIVjBQcr93hR59PDZEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:31:23.100237Z"},"content_sha256":"1469a7028c9b73570c84636ad4984eb4ee7b37f1e3630ed4af62ac1c16eb8f9c","schema_version":"1.0","event_id":"sha256:1469a7028c9b73570c84636ad4984eb4ee7b37f1e3630ed4af62ac1c16eb8f9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K/bundle.json","state_url":"https://pith.science/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:31:23Z","links":{"resolver":"https://pith.science/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K","bundle":"https://pith.science/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K/bundle.json","state":"https://pith.science/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WANAKXMK2WM7RMQQ7HWDPIV7K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3WANAKXMK2WM7RMQQ7HWDPIV7K","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":"b578ab24b9e63d9a5040d0fd0020b9460170a06ed58a42f3123b9b8c001c34c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T20:17:34Z","title_canon_sha256":"db1e4a6cdd2bfa33285aa5a3fcb81a20630a1464124c01c249761ce09273e5b7"},"schema_version":"1.0","source":{"id":"2403.05659","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05659","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05659v2","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05659","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"pith_short_12","alias_value":"3WANAKXMK2WM","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"pith_short_16","alias_value":"3WANAKXMK2WM7RMQ","created_at":"2026-07-05T08:45:10Z"},{"alias_kind":"pith_short_8","alias_value":"3WANAKXM","created_at":"2026-07-05T08:45:10Z"}],"graph_snapshots":[{"event_id":"sha256:1469a7028c9b73570c84636ad4984eb4ee7b37f1e3630ed4af62ac1c16eb8f9c","target":"graph","created_at":"2026-07-05T08:45:10Z","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/2403.05659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current visual generation methods can produce high quality videos guided by texts. However, effectively controlling object dynamics remains a challenge. This work explores audio as a cue to generate temporally synchronized image animations. We introduce Audio Synchronized Visual Animation (ASVA), a task animating a static image to demonstrate motion dynamics, temporally guided by audio clips across multiple classes. To this end, we present AVSync15, a dataset curated from VGGSound with videos featuring synchronized audio visual events across 15 categories. We also present a diffusion model, AV","authors_text":"Lin Zhang, Pedro Morgado, Shentong Mo, Yijing Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T20:17:34Z","title":"Audio-Synchronized Visual Animation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05659","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:fe7b9ab94ba6dd0de859b1f85e060981b8979b40de83ad8ee273051f5ca9b797","target":"record","created_at":"2026-07-05T08:45:10Z","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":"b578ab24b9e63d9a5040d0fd0020b9460170a06ed58a42f3123b9b8c001c34c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T20:17:34Z","title_canon_sha256":"db1e4a6cdd2bfa33285aa5a3fcb81a20630a1464124c01c249761ce09273e5b7"},"schema_version":"1.0","source":{"id":"2403.05659","kind":"arxiv","version":2}},"canonical_sha256":"dd80d02aec56accfc59087cf61bd15fab83cde203c0ece67ef0ec6047f7d9273","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd80d02aec56accfc59087cf61bd15fab83cde203c0ece67ef0ec6047f7d9273","first_computed_at":"2026-07-05T08:45:10.957104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:10.957104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V2aIfyzbrnQNtjB5fTPyr5okPwolQhMJkmTKdH2K64lJm2t0KB0ktrGW18veJIZaPL16T3LmIU9OF0O+X0vmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:10.957547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.05659","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe7b9ab94ba6dd0de859b1f85e060981b8979b40de83ad8ee273051f5ca9b797","sha256:1469a7028c9b73570c84636ad4984eb4ee7b37f1e3630ed4af62ac1c16eb8f9c"],"state_sha256":"d7c5988bfbe8a55d80dc6bf803a88a6c84519e493da11f0258a0ecf2398b0803"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pqCUFnW7w4dylAfIxb86KpZCELnc2Mkl1eZBeE/1eiIaoJ/HCITjD1p7KQO/2SgpSyy/Uf7oW5cu25woUgqDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:31:23.104507Z","bundle_sha256":"23e60c5a53d422eba007b8c333ac899718d2b51a4c4442e971fa8ab15feb2a4e"}}