{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L65JGHKFSPRXLPQCGXBZBJNNDC","short_pith_number":"pith:L65JGHKF","schema_version":"1.0","canonical_sha256":"5fba931d4593e375be0235c390a5ad18af62d7c17142b894392a22a2d08e47cf","source":{"kind":"arxiv","id":"2511.14223","version":3},"attestation_state":"computed","paper":{"title":"StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jia, Hujun Bao, Sida Peng, Xiangwei Chen, Xiaowei Zhou, Xinyu Zhu, Yifan Yang, Yifu Deng, Zhi Cen","submitted_at":"2025-11-18T07:55:16Z","abstract_excerpt":"This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by speech inputs. Recent methods have employed audio-conditioned diffusion models for 3D facial animation, achieving impressive results in generating expressive and natural animations. However, these methods process the whole audio sequences in a single pass, which poses two major challenges: they tend to perform poorly when handling audio sequences that exceed the training horizon and will suffer from significant latency when processing long audio inputs"},"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":"2511.14223","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T07:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"295bdbbf204ac6cc689bc387e1732dca0cd25841e9222a113e1310c2d1afccbb","abstract_canon_sha256":"c400fa8336256bd266cbbfb19b9f7d78e159c6601e8abf7c710680ff2e29f43a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:58.595982Z","signature_b64":"5lJ7vBFhujXB8F57oGmxZhrf7Z+4eR49XnG62RRJoVr4zJQXVoG1iOSfXCYk6cjWxyZhoIT3plLAPvF457r4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fba931d4593e375be0235c390a5ad18af62d7c17142b894392a22a2d08e47cf","last_reissued_at":"2026-05-20T00:02:58.595062Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:58.595062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jia, Hujun Bao, Sida Peng, Xiangwei Chen, Xiaowei Zhou, Xinyu Zhu, Yifan Yang, Yifu Deng, Zhi Cen","submitted_at":"2025-11-18T07:55:16Z","abstract_excerpt":"This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by speech inputs. Recent methods have employed audio-conditioned diffusion models for 3D facial animation, achieving impressive results in generating expressive and natural animations. However, these methods process the whole audio sequences in a single pass, which poses two major challenges: they tend to perform poorly when handling audio sequences that exceed the training horizon and will suffer from significant latency when processing long audio inputs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14223","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/2511.14223/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":"2511.14223","created_at":"2026-05-20T00:02:58.595214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.14223v3","created_at":"2026-05-20T00:02:58.595214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14223","created_at":"2026-05-20T00:02:58.595214+00:00"},{"alias_kind":"pith_short_12","alias_value":"L65JGHKFSPRX","created_at":"2026-05-20T00:02:58.595214+00:00"},{"alias_kind":"pith_short_16","alias_value":"L65JGHKFSPRXLPQC","created_at":"2026-05-20T00:02:58.595214+00:00"},{"alias_kind":"pith_short_8","alias_value":"L65JGHKF","created_at":"2026-05-20T00:02:58.595214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC","json":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC.json","graph_json":"https://pith.science/api/pith-number/L65JGHKFSPRXLPQCGXBZBJNNDC/graph.json","events_json":"https://pith.science/api/pith-number/L65JGHKFSPRXLPQCGXBZBJNNDC/events.json","paper":"https://pith.science/paper/L65JGHKF"},"agent_actions":{"view_html":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC","download_json":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC.json","view_paper":"https://pith.science/paper/L65JGHKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.14223&json=true","fetch_graph":"https://pith.science/api/pith-number/L65JGHKFSPRXLPQCGXBZBJNNDC/graph.json","fetch_events":"https://pith.science/api/pith-number/L65JGHKFSPRXLPQCGXBZBJNNDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC/action/storage_attestation","attest_author":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC/action/author_attestation","sign_citation":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC/action/citation_signature","submit_replication":"https://pith.science/pith/L65JGHKFSPRXLPQCGXBZBJNNDC/action/replication_record"}},"created_at":"2026-05-20T00:02:58.595214+00:00","updated_at":"2026-05-20T00:02:58.595214+00:00"}