{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GLWS3N7QBIBRSV6F53NX73ZA62","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4921548f1cd3ce075e91756d728db5eb7f4917db4d08e3774d03a7a0ebc2eaa","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-06-20T09:59:34Z","title_canon_sha256":"f0cfaa8fc0b63ef8f2f85a09927f9314ee9211e2001e199d2da0cc894544a9b2"},"schema_version":"1.0","source":{"id":"2606.21970","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21970","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21970v1","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21970","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"GLWS3N7QBIBR","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"GLWS3N7QBIBRSV6F","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"GLWS3N7Q","created_at":"2026-06-23T02:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:e304b9388bce82261aaf74d9d2303235407ae41a2bf5041b93fdc8331035b71b","target":"graph","created_at":"2026-06-23T02:13:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.21970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Atsumoto Ohashi, Jingjing Jiang, Ryuichiro Higashinaka","cross_cats":["cs.CL","cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-06-20T09:59:34Z","title":"Integrating Facial Generation into Full-Duplex Spoken Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21970","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:98986b80aae2894c1d9f6173868407b0fbd19442d2cbc6d7f57d95557baeaa2d","target":"record","created_at":"2026-06-23T02:13:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4921548f1cd3ce075e91756d728db5eb7f4917db4d08e3774d03a7a0ebc2eaa","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-06-20T09:59:34Z","title_canon_sha256":"f0cfaa8fc0b63ef8f2f85a09927f9314ee9211e2001e199d2da0cc894544a9b2"},"schema_version":"1.0","source":{"id":"2606.21970","kind":"arxiv","version":1}},"canonical_sha256":"32ed2db7f00a031957c5eedb7fef20f693d72080b14b2989a56cb512526ec010","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32ed2db7f00a031957c5eedb7fef20f693d72080b14b2989a56cb512526ec010","first_computed_at":"2026-06-23T02:13:04.614355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:04.614355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNoXnZh1yVC7Fyd8e+f2fJCRRg7XcQYKwvTOwJqD8QMA+5VN+4sB7AeLbZYEBpik0aMmylyESJlIC2unoAcnBg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:04.614764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21970","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98986b80aae2894c1d9f6173868407b0fbd19442d2cbc6d7f57d95557baeaa2d","sha256:e304b9388bce82261aaf74d9d2303235407ae41a2bf5041b93fdc8331035b71b"],"state_sha256":"bf754a18345c45e2825459484678971052d2e3494987b7b08d3cdb70aa628788"}