{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VP2VVFQ2BSW3RCBHBUBH5YX3IL","short_pith_number":"pith:VP2VVFQ2","schema_version":"1.0","canonical_sha256":"abf55a961a0cadb888270d027ee2fb42c78c0d97192a033dc2a496fef61089fb","source":{"kind":"arxiv","id":"2504.02542","version":3},"attestation_state":"computed","paper":{"title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Fa-Ting Hong, Jun Zhou, Qinglin Lu, Qin Lin, Xiu Li, Zixiang Zhou, Zunnan Xu","submitted_at":"2025-04-03T12:44:41Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.02542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T12:44:41Z","cross_cats_sorted":[],"title_canon_sha256":"854f96fb894e94fe82fb353301c3a6023e61f88b955b717291a93f31fd2e29a2","abstract_canon_sha256":"83f7632d21d00db2036053d704999c8da8b73b3a6ff00f530082811b071d0490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:20.793307Z","signature_b64":"vondqB/i/9rfBd22msd6qQxFdfJ5oGzVwTco3oNLDsdkf+wCTDeEi/V19O8m3rcbE74pQP4EAirypUS9Z2ZuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abf55a961a0cadb888270d027ee2fb42c78c0d97192a033dc2a496fef61089fb","last_reissued_at":"2026-07-05T10:45:20.792807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:20.792807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Fa-Ting Hong, Jun Zhou, Qinglin Lu, Qin Lin, Xiu Li, Zixiang Zhou, Zunnan Xu","submitted_at":"2025-04-03T12:44:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02542","kind":"arxiv","version":3},"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/2504.02542/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.02542","created_at":"2026-07-05T10:45:20.792864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02542v3","created_at":"2026-07-05T10:45:20.792864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02542","created_at":"2026-07-05T10:45:20.792864+00:00"},{"alias_kind":"pith_short_12","alias_value":"VP2VVFQ2BSW3","created_at":"2026-07-05T10:45:20.792864+00:00"},{"alias_kind":"pith_short_16","alias_value":"VP2VVFQ2BSW3RCBH","created_at":"2026-07-05T10:45:20.792864+00:00"},{"alias_kind":"pith_short_8","alias_value":"VP2VVFQ2","created_at":"2026-07-05T10:45:20.792864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL","json":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL.json","graph_json":"https://pith.science/api/pith-number/VP2VVFQ2BSW3RCBHBUBH5YX3IL/graph.json","events_json":"https://pith.science/api/pith-number/VP2VVFQ2BSW3RCBHBUBH5YX3IL/events.json","paper":"https://pith.science/paper/VP2VVFQ2"},"agent_actions":{"view_html":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL","download_json":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL.json","view_paper":"https://pith.science/paper/VP2VVFQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02542&json=true","fetch_graph":"https://pith.science/api/pith-number/VP2VVFQ2BSW3RCBHBUBH5YX3IL/graph.json","fetch_events":"https://pith.science/api/pith-number/VP2VVFQ2BSW3RCBHBUBH5YX3IL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL/action/storage_attestation","attest_author":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL/action/author_attestation","sign_citation":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL/action/citation_signature","submit_replication":"https://pith.science/pith/VP2VVFQ2BSW3RCBHBUBH5YX3IL/action/replication_record"}},"created_at":"2026-07-05T10:45:20.792864+00:00","updated_at":"2026-07-05T10:45:20.792864+00:00"}