{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:67JZNSUPGMUH5AP2YGH3IHNPJ5","short_pith_number":"pith:67JZNSUP","schema_version":"1.0","canonical_sha256":"f7d396ca8f33287e81fac18fb41daf4f70eb5e5a6ba35b25aafe4ca1185e2f45","source":{"kind":"arxiv","id":"2506.13691","version":1},"attestation_state":"computed","paper":{"title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Dacheng Tao, Haoyang He, Jiangning Zhang, Teng Hu, Xiangtai Li, Yabiao Wang, Yinan Chen, Yong Liu, Yuxuan Cai, Zhucun Xue","submitted_at":"2025-06-16T16:52:52Z","abstract_excerpt":"The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality video generation models. For example, the generation of movie-level Ultra-High Definition (UHD) videos and the creation of 4K short video content. However, the existing public datasets cannot support related research and applications. In this paper, we first propose a high-quality open-sourced UHD-4K (22.4\\% of which are 8K) text-to-video dataset named UltraVid"},"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":"2506.13691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T16:52:52Z","cross_cats_sorted":[],"title_canon_sha256":"cb40f77b86a14f41192abc2b64ede89cf747908568229f8414611ba02a85dbb1","abstract_canon_sha256":"da29e02a7b770a962a89f3a707fa8e77c4925e37c2cad7c15fb8329608eedbbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:25.000070Z","signature_b64":"IYIVGr2kj1DUYTbpWOPYVXm6c2E6NiRJe8dDjKuVOF/087esw9nXCqkKtmaYz4mOjYYIvnAuGXJZHSAMRgoyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7d396ca8f33287e81fac18fb41daf4f70eb5e5a6ba35b25aafe4ca1185e2f45","last_reissued_at":"2026-07-05T11:22:24.999569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:24.999569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Dacheng Tao, Haoyang He, Jiangning Zhang, Teng Hu, Xiangtai Li, Yabiao Wang, Yinan Chen, Yong Liu, Yuxuan Cai, Zhucun Xue","submitted_at":"2025-06-16T16:52:52Z","abstract_excerpt":"The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality video generation models. For example, the generation of movie-level Ultra-High Definition (UHD) videos and the creation of 4K short video content. However, the existing public datasets cannot support related research and applications. In this paper, we first propose a high-quality open-sourced UHD-4K (22.4\\% of which are 8K) text-to-video dataset named UltraVid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13691","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/2506.13691/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":"2506.13691","created_at":"2026-07-05T11:22:24.999637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13691v1","created_at":"2026-07-05T11:22:24.999637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13691","created_at":"2026-07-05T11:22:24.999637+00:00"},{"alias_kind":"pith_short_12","alias_value":"67JZNSUPGMUH","created_at":"2026-07-05T11:22:24.999637+00:00"},{"alias_kind":"pith_short_16","alias_value":"67JZNSUPGMUH5AP2","created_at":"2026-07-05T11:22:24.999637+00:00"},{"alias_kind":"pith_short_8","alias_value":"67JZNSUP","created_at":"2026-07-05T11:22:24.999637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09150","citing_title":"Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09639","citing_title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00858","citing_title":"MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03911","citing_title":"Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30248","citing_title":"Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27964","citing_title":"Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27891","citing_title":"SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23518","citing_title":"VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16649","citing_title":"AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20147","citing_title":"PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10248","citing_title":"RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09283","citing_title":"From Ideal to Real: Stable Video Object Removal under Imperfect Conditions","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06356","citing_title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06356","citing_title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21718","citing_title":"Building a Precise Video Language with Human-AI Oversight","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5","json":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5.json","graph_json":"https://pith.science/api/pith-number/67JZNSUPGMUH5AP2YGH3IHNPJ5/graph.json","events_json":"https://pith.science/api/pith-number/67JZNSUPGMUH5AP2YGH3IHNPJ5/events.json","paper":"https://pith.science/paper/67JZNSUP"},"agent_actions":{"view_html":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5","download_json":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5.json","view_paper":"https://pith.science/paper/67JZNSUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13691&json=true","fetch_graph":"https://pith.science/api/pith-number/67JZNSUPGMUH5AP2YGH3IHNPJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/67JZNSUPGMUH5AP2YGH3IHNPJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5/action/storage_attestation","attest_author":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5/action/author_attestation","sign_citation":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5/action/citation_signature","submit_replication":"https://pith.science/pith/67JZNSUPGMUH5AP2YGH3IHNPJ5/action/replication_record"}},"created_at":"2026-07-05T11:22:24.999637+00:00","updated_at":"2026-07-05T11:22:24.999637+00:00"}