{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LSXVF2QMU5P6LODZEBWBGBZ67K","short_pith_number":"pith:LSXVF2QM","schema_version":"1.0","canonical_sha256":"5caf52ea0ca75fe5b879206c13073efa96338a363600afc52e093b81a47973f6","source":{"kind":"arxiv","id":"2506.19833","version":1},"attestation_state":"computed","paper":{"title":"Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhong Chen, Lin Liu, Sirui Zhao, Tong Xu, Weiqiang Wang, Yubo Huang","submitted_at":"2025-06-24T17:50:16Z","abstract_excerpt":"Recent years have witnessed remarkable advances in audio-driven talking head generation. However, existing approaches predominantly focus on single-character scenarios. While some methods can create separate conversation videos between two individuals, the critical challenge of generating unified conversation videos with multiple physically co-present characters sharing the same spatial environment remains largely unaddressed. This setting presents two key challenges: audio-to-character correspondence control and the lack of suitable datasets featuring multi-character talking videos within the"},"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":"2506.19833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:50:16Z","cross_cats_sorted":[],"title_canon_sha256":"74cfbf2bd9f854a2d5c1e5d2b69532b807a8f5a0315cb388b87b86026ef42c63","abstract_canon_sha256":"ff9400d77c98576d7a7b643f62554cd8838063ecfb05e7180c7a53c9ce2b0835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.173787Z","signature_b64":"EuLC6fv0rKcAypQMqjXR32THuU8k7DZg0dAdB3QU17pZzoacOBUCwXYbHoyPp9H837Uk7ZhSgED2USd6c77aCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5caf52ea0ca75fe5b879206c13073efa96338a363600afc52e093b81a47973f6","last_reissued_at":"2026-07-05T11:26:39.173009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.173009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhong Chen, Lin Liu, Sirui Zhao, Tong Xu, Weiqiang Wang, Yubo Huang","submitted_at":"2025-06-24T17:50:16Z","abstract_excerpt":"Recent years have witnessed remarkable advances in audio-driven talking head generation. However, existing approaches predominantly focus on single-character scenarios. While some methods can create separate conversation videos between two individuals, the critical challenge of generating unified conversation videos with multiple physically co-present characters sharing the same spatial environment remains largely unaddressed. This setting presents two key challenges: audio-to-character correspondence control and the lack of suitable datasets featuring multi-character talking videos within the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19833","kind":"arxiv","version":1},"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/2506.19833/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":"2506.19833","created_at":"2026-07-05T11:26:39.173114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19833v1","created_at":"2026-07-05T11:26:39.173114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19833","created_at":"2026-07-05T11:26:39.173114+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSXVF2QMU5P6","created_at":"2026-07-05T11:26:39.173114+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSXVF2QMU5P6LODZ","created_at":"2026-07-05T11:26:39.173114+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSXVF2QM","created_at":"2026-07-05T11:26:39.173114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10079","citing_title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K","json":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K.json","graph_json":"https://pith.science/api/pith-number/LSXVF2QMU5P6LODZEBWBGBZ67K/graph.json","events_json":"https://pith.science/api/pith-number/LSXVF2QMU5P6LODZEBWBGBZ67K/events.json","paper":"https://pith.science/paper/LSXVF2QM"},"agent_actions":{"view_html":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K","download_json":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K.json","view_paper":"https://pith.science/paper/LSXVF2QM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19833&json=true","fetch_graph":"https://pith.science/api/pith-number/LSXVF2QMU5P6LODZEBWBGBZ67K/graph.json","fetch_events":"https://pith.science/api/pith-number/LSXVF2QMU5P6LODZEBWBGBZ67K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K/action/storage_attestation","attest_author":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K/action/author_attestation","sign_citation":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K/action/citation_signature","submit_replication":"https://pith.science/pith/LSXVF2QMU5P6LODZEBWBGBZ67K/action/replication_record"}},"created_at":"2026-07-05T11:26:39.173114+00:00","updated_at":"2026-07-05T11:26:39.173114+00:00"}