{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3LVSUYGFQX6DCEXMJ3SC7W2UYV","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":"4846fb239ca15d8db98f20b12dab82302205cced3d73e891dcf03b645fa6a3ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:57:27Z","title_canon_sha256":"a2a9190d9e3559c33f6dcbc9bcb250da5d5103e2260bfa6245322e8d1b82467f"},"schema_version":"1.0","source":{"id":"2505.20156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20156","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20156v2","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20156","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"3LVSUYGFQX6D","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"3LVSUYGFQX6DCEXM","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"3LVSUYGF","created_at":"2026-07-05T11:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:c38f4a562e505c54bb4f75356ac4a02565870a957cfcdc45252be0b597b9e0cb","target":"graph","created_at":"2026-07-05T11:15:00Z","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/2505.20156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have witnessed significant progress in audio-driven human animation. However, critical challenges remain in (i) generating highly dynamic videos while preserving character consistency, (ii) achieving precise emotion alignment between characters and audio, and (iii) enabling multi-character audio-driven animation. To address these challenges, we propose HunyuanVideo-Avatar, a multimodal diffusion transformer (MM-DiT)-based model capable of simultaneously generating dynamic, emotion-controllable, and multi-character dialogue videos. Concretely, HunyuanVideo-Avatar introduces three k","authors_text":"Junshu Tang, Qinglin Lu, Qin Lin, Sen Liang, Yi Chen, Yifeng Ma, Yuan Zhou, Zixiang Zhou, Ziyao Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:57:27Z","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20156","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":"sha256:94e4f000b27b25eb79a26dc7efbe6f24eb2bc672e45e68bc45e8c5fd53154600","target":"record","created_at":"2026-07-05T11:15:00Z","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":"4846fb239ca15d8db98f20b12dab82302205cced3d73e891dcf03b645fa6a3ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:57:27Z","title_canon_sha256":"a2a9190d9e3559c33f6dcbc9bcb250da5d5103e2260bfa6245322e8d1b82467f"},"schema_version":"1.0","source":{"id":"2505.20156","kind":"arxiv","version":2}},"canonical_sha256":"daeb2a60c585fc3112ec4ee42fdb54c57a47a016732e7e61ffabe8951f5c6d14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daeb2a60c585fc3112ec4ee42fdb54c57a47a016732e7e61ffabe8951f5c6d14","first_computed_at":"2026-07-05T11:15:00.323512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:00.323512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vNd8BAq0pzZZvGjnh6JvvYXhfvBFy5NjWo3v5oaaZubnN/8R12ewHCWo+r6HmjOdZrfa0yhTrgso2HHFXzEPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:00.323987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94e4f000b27b25eb79a26dc7efbe6f24eb2bc672e45e68bc45e8c5fd53154600","sha256:c38f4a562e505c54bb4f75356ac4a02565870a957cfcdc45252be0b597b9e0cb"],"state_sha256":"0f6aad587c463ba13692def4c57d9f9748186d15040a849afdc1c9b1edf902b4"}