{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VP2VVFQ2BSW3RCBHBUBH5YX3IL","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":"83f7632d21d00db2036053d704999c8da8b73b3a6ff00f530082811b071d0490","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T12:44:41Z","title_canon_sha256":"854f96fb894e94fe82fb353301c3a6023e61f88b955b717291a93f31fd2e29a2"},"schema_version":"1.0","source":{"id":"2504.02542","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02542","created_at":"2026-07-05T10:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02542v3","created_at":"2026-07-05T10:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02542","created_at":"2026-07-05T10:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"VP2VVFQ2BSW3","created_at":"2026-07-05T10:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"VP2VVFQ2BSW3RCBH","created_at":"2026-07-05T10:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"VP2VVFQ2","created_at":"2026-07-05T10:45:20Z"}],"graph_snapshots":[{"event_id":"sha256:640ae757361e736191cff2c7981dcb2d93710e6fd7e24e43df2e3325f221b936","target":"graph","created_at":"2026-07-05T10:45:20Z","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/2504.02542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Talking head synthesis is vital for virtual avatars and human-computer interaction. However, most existing methods are typically limited to accepting control from a single primary modality, restricting their practical utility. To this end, we introduce \\textbf{ACTalker}, an end-to-end video diffusion framework that supports both multi-signals control and single-signal control for talking head video generation. For multiple control, we design a parallel mamba structure with multiple branches, each utilizing a separate driving signal to control specific facial regions. A gate mechanism is applie","authors_text":"Dan Xu, Fa-Ting Hong, Jun Zhou, Qinglin Lu, Qin Lin, Xiu Li, Zixiang Zhou, Zunnan Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T12:44:41Z","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02542","kind":"arxiv","version":3},"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":"sha256:2101758c98d321c74557dd358914ef4dde1d9fd0399627e4bb0bbab8c6e6c54b","target":"record","created_at":"2026-07-05T10:45:20Z","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":"83f7632d21d00db2036053d704999c8da8b73b3a6ff00f530082811b071d0490","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T12:44:41Z","title_canon_sha256":"854f96fb894e94fe82fb353301c3a6023e61f88b955b717291a93f31fd2e29a2"},"schema_version":"1.0","source":{"id":"2504.02542","kind":"arxiv","version":3}},"canonical_sha256":"abf55a961a0cadb888270d027ee2fb42c78c0d97192a033dc2a496fef61089fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abf55a961a0cadb888270d027ee2fb42c78c0d97192a033dc2a496fef61089fb","first_computed_at":"2026-07-05T10:45:20.792807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:20.792807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vondqB/i/9rfBd22msd6qQxFdfJ5oGzVwTco3oNLDsdkf+wCTDeEi/V19O8m3rcbE74pQP4EAirypUS9Z2ZuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:20.793307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02542","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2101758c98d321c74557dd358914ef4dde1d9fd0399627e4bb0bbab8c6e6c54b","sha256:640ae757361e736191cff2c7981dcb2d93710e6fd7e24e43df2e3325f221b936"],"state_sha256":"cdfbdc5c00b5e8836bccb6f3fbcba58ba4b0d3185933358f4764ac1ff49eceed"}