{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GLWS3N7QBIBRSV6F53NX73ZA62","short_pith_number":"pith:GLWS3N7Q","schema_version":"1.0","canonical_sha256":"32ed2db7f00a031957c5eedb7fef20f693d72080b14b2989a56cb512526ec010","source":{"kind":"arxiv","id":"2606.21970","version":1},"attestation_state":"computed","paper":{"title":"Integrating Facial Generation into Full-Duplex Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.HC","authors_text":"Atsumoto Ohashi, Jingjing Jiang, Ryuichiro Higashinaka","submitted_at":"2026-06-20T09:59:34Z","abstract_excerpt":"Full-duplex spoken dialogue models, such as Moshi, enable natural, low-latency voice conversations. However, they remain limited to the audio modality, lacking the facial expressions that are integral to human communication. We present Moshi-Face, the first full-duplex dialogue model that jointly processes the user's audio and facial input while simultaneously generating speech and facial motion. We first construct a vector-quantized variational autoencoder (VQ-VAE) as a face codec that encodes 3D head meshes extracted from facial videos into compact discrete tokens, referred to as face tokens"},"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":"2606.21970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-06-20T09:59:34Z","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"f0cfaa8fc0b63ef8f2f85a09927f9314ee9211e2001e199d2da0cc894544a9b2","abstract_canon_sha256":"e4921548f1cd3ce075e91756d728db5eb7f4917db4d08e3774d03a7a0ebc2eaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:04.614764Z","signature_b64":"hNoXnZh1yVC7Fyd8e+f2fJCRRg7XcQYKwvTOwJqD8QMA+5VN+4sB7AeLbZYEBpik0aMmylyESJlIC2unoAcnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32ed2db7f00a031957c5eedb7fef20f693d72080b14b2989a56cb512526ec010","last_reissued_at":"2026-06-23T02:13:04.614355Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:04.614355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Facial Generation into Full-Duplex Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.HC","authors_text":"Atsumoto Ohashi, Jingjing Jiang, Ryuichiro Higashinaka","submitted_at":"2026-06-20T09:59:34Z","abstract_excerpt":"Full-duplex spoken dialogue models, such as Moshi, enable natural, low-latency voice conversations. However, they remain limited to the audio modality, lacking the facial expressions that are integral to human communication. We present Moshi-Face, the first full-duplex dialogue model that jointly processes the user's audio and facial input while simultaneously generating speech and facial motion. We first construct a vector-quantized variational autoencoder (VQ-VAE) as a face codec that encodes 3D head meshes extracted from facial videos into compact discrete tokens, referred to as face tokens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21970","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/2606.21970/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":"2606.21970","created_at":"2026-06-23T02:13:04.614422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21970v1","created_at":"2026-06-23T02:13:04.614422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21970","created_at":"2026-06-23T02:13:04.614422+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLWS3N7QBIBR","created_at":"2026-06-23T02:13:04.614422+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLWS3N7QBIBRSV6F","created_at":"2026-06-23T02:13:04.614422+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLWS3N7Q","created_at":"2026-06-23T02:13:04.614422+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/GLWS3N7QBIBRSV6F53NX73ZA62","json":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62.json","graph_json":"https://pith.science/api/pith-number/GLWS3N7QBIBRSV6F53NX73ZA62/graph.json","events_json":"https://pith.science/api/pith-number/GLWS3N7QBIBRSV6F53NX73ZA62/events.json","paper":"https://pith.science/paper/GLWS3N7Q"},"agent_actions":{"view_html":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62","download_json":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62.json","view_paper":"https://pith.science/paper/GLWS3N7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21970&json=true","fetch_graph":"https://pith.science/api/pith-number/GLWS3N7QBIBRSV6F53NX73ZA62/graph.json","fetch_events":"https://pith.science/api/pith-number/GLWS3N7QBIBRSV6F53NX73ZA62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62/action/storage_attestation","attest_author":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62/action/author_attestation","sign_citation":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62/action/citation_signature","submit_replication":"https://pith.science/pith/GLWS3N7QBIBRSV6F53NX73ZA62/action/replication_record"}},"created_at":"2026-06-23T02:13:04.614422+00:00","updated_at":"2026-06-23T02:13:04.614422+00:00"}