{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XDVQVNZ74QQG4YV4PGXKAUV74A","short_pith_number":"pith:XDVQVNZ7","schema_version":"1.0","canonical_sha256":"b8eb0ab73fe4206e62bc79aea052bfe0359bcd9af1097044af67bddbd53b88c1","source":{"kind":"arxiv","id":"2606.03874","version":1},"attestation_state":"computed","paper":{"title":"DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Amrita Mazumdar, Christian Jacobsen, Hongyu Liu, Ka Chun Cheung, Koki Nagano, Michael Stengel, Rajarshi Roy, Seonwook Park, Shalini De Mello, Shengze Wang, Simon See, Tianye Li","submitted_at":"2026-06-02T16:42:56Z","abstract_excerpt":"We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of human communication, this full-duplex capability empowers the agent to simultaneously perceive and generate both speech and physical motion in a streaming fashion. At its core, our method leverages the strong priors of a foundational full-duplex speech model and integrates a novel motion pathway, thereby achieving fully synchronized multi-modal interaction. Specifically, we design a dual-tower Transformer architecture that preserves the zero-s"},"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":"2606.03874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T16:42:56Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6cbaa8cc66d6a02a1b57a3bf186f209169157c674815494b50342c7a2320312b","abstract_canon_sha256":"e160c4276dfaaa5497498c4b9e5d62c99de55048852fe30f9b02da0bda5c0f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:04.997786Z","signature_b64":"3c/RCblMeHCozLDUFzLpehsayJaXgkFLtPJ7P/5Xo45oksujvajrH3VgVw+Y3LiMGa/moSx02Jf2/nzMCrZeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8eb0ab73fe4206e62bc79aea052bfe0359bcd9af1097044af67bddbd53b88c1","last_reissued_at":"2026-06-03T02:06:04.997443Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:04.997443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Amrita Mazumdar, Christian Jacobsen, Hongyu Liu, Ka Chun Cheung, Koki Nagano, Michael Stengel, Rajarshi Roy, Seonwook Park, Shalini De Mello, Shengze Wang, Simon See, Tianye Li","submitted_at":"2026-06-02T16:42:56Z","abstract_excerpt":"We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of human communication, this full-duplex capability empowers the agent to simultaneously perceive and generate both speech and physical motion in a streaming fashion. At its core, our method leverages the strong priors of a foundational full-duplex speech model and integrates a novel motion pathway, thereby achieving fully synchronized multi-modal interaction. Specifically, we design a dual-tower Transformer architecture that preserves the zero-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03874","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/2606.03874/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":"2606.03874","created_at":"2026-06-03T02:06:04.997506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03874v1","created_at":"2026-06-03T02:06:04.997506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03874","created_at":"2026-06-03T02:06:04.997506+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDVQVNZ74QQG","created_at":"2026-06-03T02:06:04.997506+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDVQVNZ74QQG4YV4","created_at":"2026-06-03T02:06:04.997506+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDVQVNZ7","created_at":"2026-06-03T02:06:04.997506+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/XDVQVNZ74QQG4YV4PGXKAUV74A","json":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A.json","graph_json":"https://pith.science/api/pith-number/XDVQVNZ74QQG4YV4PGXKAUV74A/graph.json","events_json":"https://pith.science/api/pith-number/XDVQVNZ74QQG4YV4PGXKAUV74A/events.json","paper":"https://pith.science/paper/XDVQVNZ7"},"agent_actions":{"view_html":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A","download_json":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A.json","view_paper":"https://pith.science/paper/XDVQVNZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03874&json=true","fetch_graph":"https://pith.science/api/pith-number/XDVQVNZ74QQG4YV4PGXKAUV74A/graph.json","fetch_events":"https://pith.science/api/pith-number/XDVQVNZ74QQG4YV4PGXKAUV74A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A/action/storage_attestation","attest_author":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A/action/author_attestation","sign_citation":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A/action/citation_signature","submit_replication":"https://pith.science/pith/XDVQVNZ74QQG4YV4PGXKAUV74A/action/replication_record"}},"created_at":"2026-06-03T02:06:04.997506+00:00","updated_at":"2026-06-03T02:06:04.997506+00:00"}