{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5B6BJL3HI7Z5XR3KBOZRCXLQR5","short_pith_number":"pith:5B6BJL3H","schema_version":"1.0","canonical_sha256":"e87c14af6747f3dbc76a0bb3115d708f7a3ae03d7d801d387d2ee16b1d492ba1","source":{"kind":"arxiv","id":"2503.21144","version":1},"attestation_state":"computed","paper":{"title":"ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Chaonan Ji, Jinwei Qi, Liefeng Bo, Peng Zhang, Sheng Xu","submitted_at":"2025-03-27T04:18:53Z","abstract_excerpt":"Real-time interactive video-chat portraits have been increasingly recognized as the future trend, particularly due to the remarkable progress made in text and voice chat technologies. However, existing methods primarily focus on real-time generation of head movements, but struggle to produce synchronized body motions that match these head actions. Additionally, achieving fine-grained control over the speaking style and nuances of facial expressions remains a challenge. To address these limitations, we introduce a novel framework for stylized real-time portrait video generation, enabling expres"},"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":"2503.21144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T04:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"186ffe90bf864de6c7c26f295d2f23baff6ef111b8a6bcfe3ca4719b3a94c75d","abstract_canon_sha256":"92e2d1dc96742309038acf672935149c91292a6c9256d60800a76858220e75e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:20.446879Z","signature_b64":"TeVBzooKZ8xjitvT3hnlOIkFDUt6XnRilLuAAXGEg3JSDSBIVZg57w6gPZvfnR8hSXoFFnV8r9E0wt/wIhixAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e87c14af6747f3dbc76a0bb3115d708f7a3ae03d7d801d387d2ee16b1d492ba1","last_reissued_at":"2026-07-05T10:40:20.446397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:20.446397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Chaonan Ji, Jinwei Qi, Liefeng Bo, Peng Zhang, Sheng Xu","submitted_at":"2025-03-27T04:18:53Z","abstract_excerpt":"Real-time interactive video-chat portraits have been increasingly recognized as the future trend, particularly due to the remarkable progress made in text and voice chat technologies. However, existing methods primarily focus on real-time generation of head movements, but struggle to produce synchronized body motions that match these head actions. Additionally, achieving fine-grained control over the speaking style and nuances of facial expressions remains a challenge. To address these limitations, we introduce a novel framework for stylized real-time portrait video generation, enabling expres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21144","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/2503.21144/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":"2503.21144","created_at":"2026-07-05T10:40:20.446457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21144v1","created_at":"2026-07-05T10:40:20.446457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21144","created_at":"2026-07-05T10:40:20.446457+00:00"},{"alias_kind":"pith_short_12","alias_value":"5B6BJL3HI7Z5","created_at":"2026-07-05T10:40:20.446457+00:00"},{"alias_kind":"pith_short_16","alias_value":"5B6BJL3HI7Z5XR3K","created_at":"2026-07-05T10:40:20.446457+00:00"},{"alias_kind":"pith_short_8","alias_value":"5B6BJL3H","created_at":"2026-07-05T10:40:20.446457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01620","citing_title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5","json":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5.json","graph_json":"https://pith.science/api/pith-number/5B6BJL3HI7Z5XR3KBOZRCXLQR5/graph.json","events_json":"https://pith.science/api/pith-number/5B6BJL3HI7Z5XR3KBOZRCXLQR5/events.json","paper":"https://pith.science/paper/5B6BJL3H"},"agent_actions":{"view_html":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5","download_json":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5.json","view_paper":"https://pith.science/paper/5B6BJL3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21144&json=true","fetch_graph":"https://pith.science/api/pith-number/5B6BJL3HI7Z5XR3KBOZRCXLQR5/graph.json","fetch_events":"https://pith.science/api/pith-number/5B6BJL3HI7Z5XR3KBOZRCXLQR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5/action/storage_attestation","attest_author":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5/action/author_attestation","sign_citation":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5/action/citation_signature","submit_replication":"https://pith.science/pith/5B6BJL3HI7Z5XR3KBOZRCXLQR5/action/replication_record"}},"created_at":"2026-07-05T10:40:20.446457+00:00","updated_at":"2026-07-05T10:40:20.446457+00:00"}