{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UKWVU77NDXNTWH6WEBY7UU2WT2","short_pith_number":"pith:UKWVU77N","schema_version":"1.0","canonical_sha256":"a2ad5a7fed1ddb3b1fd62071fa53569ebc405a30255e102b306a9ffb726e99dd","source":{"kind":"arxiv","id":"2606.09186","version":1},"attestation_state":"computed","paper":{"title":"DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jinghua Hao, Jiuchong Gao, Jun Liu, Jun Xu, Lei Shi, Lingling Zhang, Muye Huang, Renqing He, Xingyu Yu, Zhanyu Ma","submitted_at":"2026-06-08T08:23:02Z","abstract_excerpt":"Human interaction is continuous, multimodal, and full-duplex by nature. Although recent omni models have made substantial progress in unified speech, vision, and text modeling, combining seamless real-time interaction with complex reasoning and tool use remains challenging. We present DuplexOmni, a method for real-time multimodal full-duplex interaction. DuplexOmni separates model capability into an interaction layer and a thinking layer, which collaborate asynchronously in parallel. The interaction layer is implemented by the DuplexOmni model, an end-to-end system that processes streaming aud"},"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":"2606.09186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-08T08:23:02Z","cross_cats_sorted":[],"title_canon_sha256":"2ec6925fbaf89dbb7ff99ac532a2137840080ab49cfb3c13ce656eb366c33887","abstract_canon_sha256":"a5ecfc130525f1fb5330e982fdf785de1755df6baa72a147b4ac34c5be8a2c67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:05.947555Z","signature_b64":"cDpnWsS2yr3ABUQu80OdesEEVAg/J6lW/RH9Y70Zp6dxGB/+ogiwYE6sb0I7kTYmyKYe2GIwBKXF5d7hBbKyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ad5a7fed1ddb3b1fd62071fa53569ebc405a30255e102b306a9ffb726e99dd","last_reissued_at":"2026-06-09T02:08:05.946598Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:05.946598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jinghua Hao, Jiuchong Gao, Jun Liu, Jun Xu, Lei Shi, Lingling Zhang, Muye Huang, Renqing He, Xingyu Yu, Zhanyu Ma","submitted_at":"2026-06-08T08:23:02Z","abstract_excerpt":"Human interaction is continuous, multimodal, and full-duplex by nature. Although recent omni models have made substantial progress in unified speech, vision, and text modeling, combining seamless real-time interaction with complex reasoning and tool use remains challenging. We present DuplexOmni, a method for real-time multimodal full-duplex interaction. DuplexOmni separates model capability into an interaction layer and a thinking layer, which collaborate asynchronously in parallel. The interaction layer is implemented by the DuplexOmni model, an end-to-end system that processes streaming aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09186","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/2606.09186/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":"2606.09186","created_at":"2026-06-09T02:08:05.946761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09186v1","created_at":"2026-06-09T02:08:05.946761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09186","created_at":"2026-06-09T02:08:05.946761+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKWVU77NDXNT","created_at":"2026-06-09T02:08:05.946761+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKWVU77NDXNTWH6W","created_at":"2026-06-09T02:08:05.946761+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKWVU77N","created_at":"2026-06-09T02:08:05.946761+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/UKWVU77NDXNTWH6WEBY7UU2WT2","json":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2.json","graph_json":"https://pith.science/api/pith-number/UKWVU77NDXNTWH6WEBY7UU2WT2/graph.json","events_json":"https://pith.science/api/pith-number/UKWVU77NDXNTWH6WEBY7UU2WT2/events.json","paper":"https://pith.science/paper/UKWVU77N"},"agent_actions":{"view_html":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2","download_json":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2.json","view_paper":"https://pith.science/paper/UKWVU77N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09186&json=true","fetch_graph":"https://pith.science/api/pith-number/UKWVU77NDXNTWH6WEBY7UU2WT2/graph.json","fetch_events":"https://pith.science/api/pith-number/UKWVU77NDXNTWH6WEBY7UU2WT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2/action/storage_attestation","attest_author":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2/action/author_attestation","sign_citation":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2/action/citation_signature","submit_replication":"https://pith.science/pith/UKWVU77NDXNTWH6WEBY7UU2WT2/action/replication_record"}},"created_at":"2026-06-09T02:08:05.946761+00:00","updated_at":"2026-06-09T02:08:05.946761+00:00"}