{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7HFCRF5GMVFETEZQUKPZZXZB6","short_pith_number":"pith:Y7HFCRF5","schema_version":"1.0","canonical_sha256":"c7ce5144bd332a524c998514fce6f90fb3d61a5a595f911b3dc8c55eb25ca199","source":{"kind":"arxiv","id":"2607.26818","version":1},"attestation_state":"computed","paper":{"title":"Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Quanyue Song, Yali Wang, Yanbo Ding, Yishan He, Yongxiang Li, Zhixiang He, Zhizhi Guo","submitted_at":"2026-07-29T12:13:01Z","abstract_excerpt":"Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video generation methods have been proposed, they remain costly and fail to support long-form generation. To address this, we propose \\textbf{Ripple}, a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism. To enable efficient streaming inference while preserving long-term context, Ripple combines a fixed-length sliding-window attention with modality-specific memory states that continuou"},"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":"2607.26818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T12:13:01Z","cross_cats_sorted":[],"title_canon_sha256":"2bf480ce76456f9d7a89dd68354c18f83e02450bae6eb62b618a3c96b336eab9","abstract_canon_sha256":"5a85d1074d6baec095d0171b973b362b72d4a7b4fa973bbc66130e09f6607ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ce5144bd332a524c998514fce6f90fb3d61a5a595f911b3dc8c55eb25ca199","last_reissued_at":"2026-07-30T01:22:25.974632Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:25.974632Z"},"graph_snapshot":{"paper":{"title":"Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Quanyue Song, Yali Wang, Yanbo Ding, Yishan He, Yongxiang Li, Zhixiang He, Zhizhi Guo","submitted_at":"2026-07-29T12:13:01Z","abstract_excerpt":"Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video generation methods have been proposed, they remain costly and fail to support long-form generation. To address this, we propose \\textbf{Ripple}, a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism. To enable efficient streaming inference while preserving long-term context, Ripple combines a fixed-length sliding-window attention with modality-specific memory states that continuou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26818","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/2607.26818/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":"2607.26818","created_at":"2026-07-30T01:22:25.979694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26818v1","created_at":"2026-07-30T01:22:25.979694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26818","created_at":"2026-07-30T01:22:25.979694+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7HFCRF5GMVF","created_at":"2026-07-30T01:22:25.979694+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7HFCRF5GMVFETEZ","created_at":"2026-07-30T01:22:25.979694+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7HFCRF5","created_at":"2026-07-30T01:22:25.979694+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/Y7HFCRF5GMVFETEZQUKPZZXZB6","json":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6.json","graph_json":"https://pith.science/api/pith-number/Y7HFCRF5GMVFETEZQUKPZZXZB6/graph.json","events_json":"https://pith.science/api/pith-number/Y7HFCRF5GMVFETEZQUKPZZXZB6/events.json","paper":"https://pith.science/paper/Y7HFCRF5"},"agent_actions":{"view_html":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6","download_json":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6.json","view_paper":"https://pith.science/paper/Y7HFCRF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26818&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7HFCRF5GMVFETEZQUKPZZXZB6/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7HFCRF5GMVFETEZQUKPZZXZB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6/action/storage_attestation","attest_author":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6/action/author_attestation","sign_citation":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6/action/citation_signature","submit_replication":"https://pith.science/pith/Y7HFCRF5GMVFETEZQUKPZZXZB6/action/replication_record"}},"created_at":"2026-07-30T01:22:25.979694+00:00","updated_at":"2026-07-30T01:22:25.979694+00:00"}