{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SQQI7IUB2762SR4YAAC345RLYH","short_pith_number":"pith:SQQI7IUB","schema_version":"1.0","canonical_sha256":"94208fa281d7fda947980005be762bc1fdc78e16ae289168cd79a64cb40e144b","source":{"kind":"arxiv","id":"2602.11564","version":2},"attestation_state":"computed","paper":{"title":"LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Zhao, Hongyu Li, Jian Yang, Jiawei Chen, Kai Zhang, Shilin Lu, Xiaoming Wei, Ying Tai, Zhuoliang Kang","submitted_at":"2026-02-12T04:35:16Z","abstract_excerpt":"Recent advances in video diffusion models have significantly improved visual quality, yet ultra-high-resolution (UHR) video generation remains a formidable challenge due to the compounded difficulties of motion modeling, semantic planning, and detail synthesis. To address these limitations, we propose \\textbf{LUVE}, a \\textbf{L}atent-cascaded \\textbf{U}HR \\textbf{V}ideo generation framework built upon dual frequency \\textbf{E}xperts. LUVE employs a three-stage architecture comprising low-resolution motion generation for motion-consistent latent synthesis, video latent upsampling that performs "},"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":"2602.11564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-12T04:35:16Z","cross_cats_sorted":[],"title_canon_sha256":"ee0f1b0a9d6848a072ccb771f90a294dbfd5a753b86404be0b710513c65bec1c","abstract_canon_sha256":"2464b37d0c60e7e11f576a3f1703e84cbaf1c7fa249b6e578351eaa9de55250a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:36.765791Z","signature_b64":"isiSaE4iHCY6ejpUUKrRffmaFoPnG/s8vaNBedJDpsUcEdZi75RJ90ZFhhAyqTnXvuWdJGYUXh/dGeXFZu5gCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94208fa281d7fda947980005be762bc1fdc78e16ae289168cd79a64cb40e144b","last_reissued_at":"2026-05-28T01:04:36.765332Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:36.765332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Zhao, Hongyu Li, Jian Yang, Jiawei Chen, Kai Zhang, Shilin Lu, Xiaoming Wei, Ying Tai, Zhuoliang Kang","submitted_at":"2026-02-12T04:35:16Z","abstract_excerpt":"Recent advances in video diffusion models have significantly improved visual quality, yet ultra-high-resolution (UHR) video generation remains a formidable challenge due to the compounded difficulties of motion modeling, semantic planning, and detail synthesis. To address these limitations, we propose \\textbf{LUVE}, a \\textbf{L}atent-cascaded \\textbf{U}HR \\textbf{V}ideo generation framework built upon dual frequency \\textbf{E}xperts. LUVE employs a three-stage architecture comprising low-resolution motion generation for motion-consistent latent synthesis, video latent upsampling that performs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11564","kind":"arxiv","version":2},"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/2602.11564/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":"2602.11564","created_at":"2026-05-28T01:04:36.765406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11564v2","created_at":"2026-05-28T01:04:36.765406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11564","created_at":"2026-05-28T01:04:36.765406+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQQI7IUB2762","created_at":"2026-05-28T01:04:36.765406+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQQI7IUB2762SR4Y","created_at":"2026-05-28T01:04:36.765406+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQQI7IUB","created_at":"2026-05-28T01:04:36.765406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.16649","citing_title":"AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08250","citing_title":"Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06870","citing_title":"RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18047","citing_title":"GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting","ref_index":160,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15654","citing_title":"From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH","json":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH.json","graph_json":"https://pith.science/api/pith-number/SQQI7IUB2762SR4YAAC345RLYH/graph.json","events_json":"https://pith.science/api/pith-number/SQQI7IUB2762SR4YAAC345RLYH/events.json","paper":"https://pith.science/paper/SQQI7IUB"},"agent_actions":{"view_html":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH","download_json":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH.json","view_paper":"https://pith.science/paper/SQQI7IUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11564&json=true","fetch_graph":"https://pith.science/api/pith-number/SQQI7IUB2762SR4YAAC345RLYH/graph.json","fetch_events":"https://pith.science/api/pith-number/SQQI7IUB2762SR4YAAC345RLYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH/action/storage_attestation","attest_author":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH/action/author_attestation","sign_citation":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH/action/citation_signature","submit_replication":"https://pith.science/pith/SQQI7IUB2762SR4YAAC345RLYH/action/replication_record"}},"created_at":"2026-05-28T01:04:36.765406+00:00","updated_at":"2026-05-28T01:04:36.765406+00:00"}