{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GHA2MR6OGLDXESPQW4JCKGL7ES","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":"309d52a4dd3609bf71212df849cbcb570141f3a887bc7d8aa8941405afe1b670","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:57:06Z","title_canon_sha256":"9e72678420a0fc40527f825abba8996bd16ceb13ae5bfd760b76c77ea82d9926"},"schema_version":"1.0","source":{"id":"2505.22647","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22647","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22647v1","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22647","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"GHA2MR6OGLDX","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"pith_short_16","alias_value":"GHA2MR6OGLDXESPQ","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"pith_short_8","alias_value":"GHA2MR6O","created_at":"2026-07-05T11:11:28Z"}],"graph_snapshots":[{"event_id":"sha256:7a1f7cd962ac6387c0d5e242b08c51c3469dc6bb3130e58377651d90fc04fd02","target":"graph","created_at":"2026-07-05T11:11:28Z","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/2505.22647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-driven human animation methods, such as talking head and talking body generation, have made remarkable progress in generating synchronized facial movements and appealing visual quality videos. However, existing methods primarily focus on single human animation and struggle with multi-stream audio inputs, facing incorrect binding problems between audio and persons. Additionally, they exhibit limitations in instruction-following capabilities. To solve this problem, in this paper, we propose a novel task: Multi-Person Conversational Video Generation, and introduce a new framework, MultiTalk","authors_text":"Feng Gao, Guanying Chen, Wenhan Luo, Xiaoming Wei, Xunliang Cai, Yong Zhang, Zhe Kong, Zhuoliang Kang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:57:06Z","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22647","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":"sha256:4a3d7d816e5fa5709ce21c4afb419df6af70e5602f7ec7e9880ada5b2d163cf1","target":"record","created_at":"2026-07-05T11:11:28Z","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":"309d52a4dd3609bf71212df849cbcb570141f3a887bc7d8aa8941405afe1b670","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:57:06Z","title_canon_sha256":"9e72678420a0fc40527f825abba8996bd16ceb13ae5bfd760b76c77ea82d9926"},"schema_version":"1.0","source":{"id":"2505.22647","kind":"arxiv","version":1}},"canonical_sha256":"31c1a647ce32c77249f0b71225197f2489b627b58a2e11401178940f0c315733","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31c1a647ce32c77249f0b71225197f2489b627b58a2e11401178940f0c315733","first_computed_at":"2026-07-05T11:11:28.429621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:28.429621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0gmIEBVmaemnzbf6LVbDsjxXuaHleP5ixl+tq7+wCyd9j7+RyeW+otvfKi8x9mhcqM20ic5hsJIsOLlamaxLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:28.430169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22647","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a3d7d816e5fa5709ce21c4afb419df6af70e5602f7ec7e9880ada5b2d163cf1","sha256:7a1f7cd962ac6387c0d5e242b08c51c3469dc6bb3130e58377651d90fc04fd02"],"state_sha256":"fc3dd03af05208316b586df578bda8e05546b60f4f4dc2828ca27e628272444c"}