{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PRRUHGFSVAAKEG3MUBG2DIAAM","short_pith_number":"pith:3PRRUHGF","schema_version":"1.0","canonical_sha256":"dbe31a1cc595400510db65026d0d000307f34821af67bd3c30c8523e7236dbaa","source":{"kind":"arxiv","id":"2411.13503","version":1},"attestation_state":"computed","paper":{"title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Dahua Lin, Fan Zhang, Jiashuo Yu, Limin Wang, Nattapol Chanpaisit, Qianli Ma, Xiaojie Xu, Xinyuan Chen, Yaohui Wang, Yinan He, Ying-Cong Chen, Yuming Jiang, Yu Qiao, Ziqi Huang, Ziwei Liu, Ziyue Dong","submitted_at":"2024-11-20T17:54:41Z","abstract_excerpt":"Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects \"video generation quality\" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has several a"},"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":"2411.13503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T17:54:41Z","cross_cats_sorted":[],"title_canon_sha256":"77b3a5aa696c490a0d9fcd43d53d7020b0098fb043f5b978b7ab18774639342a","abstract_canon_sha256":"cf11cc8e95eacded9f9f28006fb95d0eccce778b1a2333e03d055fc8cdf13318"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:18.326836Z","signature_b64":"S02QYzQGeO3c+eo0IcKeYHmP2u1K613K2WUJIn+AozzADSCd9kwsraQWGWnmTZ3OYJs2nbr3jqrBgujjExKlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe31a1cc595400510db65026d0d000307f34821af67bd3c30c8523e7236dbaa","last_reissued_at":"2026-07-05T09:38:18.326399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:18.326399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Dahua Lin, Fan Zhang, Jiashuo Yu, Limin Wang, Nattapol Chanpaisit, Qianli Ma, Xiaojie Xu, Xinyuan Chen, Yaohui Wang, Yinan He, Ying-Cong Chen, Yuming Jiang, Yu Qiao, Ziqi Huang, Ziwei Liu, Ziyue Dong","submitted_at":"2024-11-20T17:54:41Z","abstract_excerpt":"Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects \"video generation quality\" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has several a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13503","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/2411.13503/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":"2411.13503","created_at":"2026-07-05T09:38:18.326456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13503v1","created_at":"2026-07-05T09:38:18.326456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13503","created_at":"2026-07-05T09:38:18.326456+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PRRUHGFSVAA","created_at":"2026-07-05T09:38:18.326456+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PRRUHGFSVAAKEG3","created_at":"2026-07-05T09:38:18.326456+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PRRUHGF","created_at":"2026-07-05T09:38:18.326456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18943","citing_title":"Physics-IQ Verified","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31672","citing_title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01499","citing_title":"Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17536","citing_title":"OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28531","citing_title":"A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31326","citing_title":"Bridging Video Understanding and Generation in a Unified Framework","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31672","citing_title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14988","citing_title":"Compositional Video Generation via Inference-Time Guidance","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25343","citing_title":"Toward Native Multimodal Modeling: A Roadmap","ref_index":151,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19320","citing_title":"SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09038","citing_title":"Do generative video models understand physical principles?","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20206","citing_title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04678","citing_title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05635","citing_title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22622","citing_title":"LongLive: Real-time Interactive Long Video Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14269","citing_title":"PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13211","citing_title":"MAGI-1: Autoregressive Video Generation at Scale","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03475","citing_title":"WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM","json":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM.json","graph_json":"https://pith.science/api/pith-number/3PRRUHGFSVAAKEG3MUBG2DIAAM/graph.json","events_json":"https://pith.science/api/pith-number/3PRRUHGFSVAAKEG3MUBG2DIAAM/events.json","paper":"https://pith.science/paper/3PRRUHGF"},"agent_actions":{"view_html":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM","download_json":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM.json","view_paper":"https://pith.science/paper/3PRRUHGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13503&json=true","fetch_graph":"https://pith.science/api/pith-number/3PRRUHGFSVAAKEG3MUBG2DIAAM/graph.json","fetch_events":"https://pith.science/api/pith-number/3PRRUHGFSVAAKEG3MUBG2DIAAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM/action/storage_attestation","attest_author":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM/action/author_attestation","sign_citation":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM/action/citation_signature","submit_replication":"https://pith.science/pith/3PRRUHGFSVAAKEG3MUBG2DIAAM/action/replication_record"}},"created_at":"2026-07-05T09:38:18.326456+00:00","updated_at":"2026-07-05T09:38:18.326456+00:00"}