{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PP6XYQIKPPY53LRA5LXJBDSD7W","short_pith_number":"pith:PP6XYQIK","schema_version":"1.0","canonical_sha256":"7bfd7c410a7bf1ddae20eaee908e43fdb13b10888d2f20684cbb1e23b7ba183b","source":{"kind":"arxiv","id":"2607.23023","version":1},"attestation_state":"computed","paper":{"title":"OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caigui Jiang, Quanyue Song, Yanbo Ding, Yishan He, Yongxiang Li, Zhixiang He, Zhi Zhi Guo","submitted_at":"2026-07-25T03:42:52Z","abstract_excerpt":"Recent advances in diffusion-based generative models have enabled real-time audio-driven avatar generation and unified audio-visual synthesis, providing a promising foundation for interactive avatar systems. However, extending these models to real-time interactive streaming remains challenging, as the generation horizon is unknown in advance and cross-modal identity consistency gradually degrades during long-term generation. To address these challenges, we propose OmniMate, a unified framework for open-ended real-time interactive audio-visual avatar generation. OmniMate jointly synthesizes vis"},"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":"2607.23023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T03:42:52Z","cross_cats_sorted":[],"title_canon_sha256":"142e554fcc93167c413114703a87901ce40cfe8f4d1e9f235ccc5b8f1c1b98ed","abstract_canon_sha256":"150a3bf167b827918c2fae79a4828fa7601ae16f49bd81427059688a4aaa3dc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:08.207492Z","signature_b64":"DCbu96XWwSg89/Yvb+oG2KxWMZloYAXipgaLaRo9Yn3pmVav6jrt8hINf9CnIX+I63yDSMFZFH/GOhXj+J1YDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bfd7c410a7bf1ddae20eaee908e43fdb13b10888d2f20684cbb1e23b7ba183b","last_reissued_at":"2026-07-28T00:22:08.206625Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:08.206625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caigui Jiang, Quanyue Song, Yanbo Ding, Yishan He, Yongxiang Li, Zhixiang He, Zhi Zhi Guo","submitted_at":"2026-07-25T03:42:52Z","abstract_excerpt":"Recent advances in diffusion-based generative models have enabled real-time audio-driven avatar generation and unified audio-visual synthesis, providing a promising foundation for interactive avatar systems. However, extending these models to real-time interactive streaming remains challenging, as the generation horizon is unknown in advance and cross-modal identity consistency gradually degrades during long-term generation. To address these challenges, we propose OmniMate, a unified framework for open-ended real-time interactive audio-visual avatar generation. OmniMate jointly synthesizes vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23023","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/2607.23023/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":"2607.23023","created_at":"2026-07-28T00:22:08.207062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23023v1","created_at":"2026-07-28T00:22:08.207062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23023","created_at":"2026-07-28T00:22:08.207062+00:00"},{"alias_kind":"pith_short_12","alias_value":"PP6XYQIKPPY5","created_at":"2026-07-28T00:22:08.207062+00:00"},{"alias_kind":"pith_short_16","alias_value":"PP6XYQIKPPY53LRA","created_at":"2026-07-28T00:22:08.207062+00:00"},{"alias_kind":"pith_short_8","alias_value":"PP6XYQIK","created_at":"2026-07-28T00:22:08.207062+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/PP6XYQIKPPY53LRA5LXJBDSD7W","json":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W.json","graph_json":"https://pith.science/api/pith-number/PP6XYQIKPPY53LRA5LXJBDSD7W/graph.json","events_json":"https://pith.science/api/pith-number/PP6XYQIKPPY53LRA5LXJBDSD7W/events.json","paper":"https://pith.science/paper/PP6XYQIK"},"agent_actions":{"view_html":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W","download_json":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W.json","view_paper":"https://pith.science/paper/PP6XYQIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23023&json=true","fetch_graph":"https://pith.science/api/pith-number/PP6XYQIKPPY53LRA5LXJBDSD7W/graph.json","fetch_events":"https://pith.science/api/pith-number/PP6XYQIKPPY53LRA5LXJBDSD7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W/action/storage_attestation","attest_author":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W/action/author_attestation","sign_citation":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W/action/citation_signature","submit_replication":"https://pith.science/pith/PP6XYQIKPPY53LRA5LXJBDSD7W/action/replication_record"}},"created_at":"2026-07-28T00:22:08.207062+00:00","updated_at":"2026-07-28T00:22:08.207062+00:00"}