{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y3SK2B4SIY5LH72O2BNLVEUJA4","short_pith_number":"pith:Y3SK2B4S","schema_version":"1.0","canonical_sha256":"c6e4ad0792463ab3ff4ed05aba928907266814ccc62019ca029065c6a8ee22f6","source":{"kind":"arxiv","id":"2607.03118","version":1},"attestation_state":"computed","paper":{"title":"Vidu S1: A Real-Time Interactive Video Generation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chendong Xiang, Chengyang Ye, Dechuang Chen, Fan Bao, Fangcheng Fu, Haoxu Wang, Hongzhou Zhu, Jianfei Chen, Jintao Chen, Jintao Zhang, Jungang Li, Jun Zhu, Kai Jiang, Kaiwen Zheng, Marco Chen, Min Zhao, Qi Jia, Xiaohang Wang, Xin Chen, Xu Wang, Yang Luo, Yimin Chen, Youhe Jiang, Yuji Wang, Yuxuan Jiang, Zhengkun Huang, Zhijie Deng","submitted_at":"2026-07-03T08:58:06Z","abstract_excerpt":"We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the"},"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":"2607.03118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T08:58:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4a11a5c7e240be5280a1bead57009436855479341b3addf80617f6bb446a4e4","abstract_canon_sha256":"6b0398ef181aa851bc6a3303ddd94c5ac7ad430f067b21405f9ac94508002fd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:43.671503Z","signature_b64":"4JF1qzL3G9u9WndJj6Ys+LPiJZpWRT99GZ+kQa1864/7TSL3vQktZFXmNXYGvR5RAWt4o/kPT1otlvKZdnhWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6e4ad0792463ab3ff4ed05aba928907266814ccc62019ca029065c6a8ee22f6","last_reissued_at":"2026-07-07T01:16:43.670985Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:43.670985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vidu S1: A Real-Time Interactive Video Generation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chendong Xiang, Chengyang Ye, Dechuang Chen, Fan Bao, Fangcheng Fu, Haoxu Wang, Hongzhou Zhu, Jianfei Chen, Jintao Chen, Jintao Zhang, Jungang Li, Jun Zhu, Kai Jiang, Kaiwen Zheng, Marco Chen, Min Zhao, Qi Jia, Xiaohang Wang, Xin Chen, Xu Wang, Yang Luo, Yimin Chen, Youhe Jiang, Yuji Wang, Yuxuan Jiang, Zhengkun Huang, Zhijie Deng","submitted_at":"2026-07-03T08:58:06Z","abstract_excerpt":"We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03118","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/2607.03118/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":"2607.03118","created_at":"2026-07-07T01:16:43.671069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03118v1","created_at":"2026-07-07T01:16:43.671069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03118","created_at":"2026-07-07T01:16:43.671069+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3SK2B4SIY5L","created_at":"2026-07-07T01:16:43.671069+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3SK2B4SIY5LH72O","created_at":"2026-07-07T01:16:43.671069+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3SK2B4S","created_at":"2026-07-07T01:16:43.671069+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/Y3SK2B4SIY5LH72O2BNLVEUJA4","json":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4.json","graph_json":"https://pith.science/api/pith-number/Y3SK2B4SIY5LH72O2BNLVEUJA4/graph.json","events_json":"https://pith.science/api/pith-number/Y3SK2B4SIY5LH72O2BNLVEUJA4/events.json","paper":"https://pith.science/paper/Y3SK2B4S"},"agent_actions":{"view_html":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4","download_json":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4.json","view_paper":"https://pith.science/paper/Y3SK2B4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03118&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3SK2B4SIY5LH72O2BNLVEUJA4/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3SK2B4SIY5LH72O2BNLVEUJA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4/action/storage_attestation","attest_author":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4/action/author_attestation","sign_citation":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4/action/citation_signature","submit_replication":"https://pith.science/pith/Y3SK2B4SIY5LH72O2BNLVEUJA4/action/replication_record"}},"created_at":"2026-07-07T01:16:43.671069+00:00","updated_at":"2026-07-07T01:16:43.671069+00:00"}