{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DYH2Y3QG75AS2UUUEQZEIQLYCE","short_pith_number":"pith:DYH2Y3QG","schema_version":"1.0","canonical_sha256":"1e0fac6e06ff412d52942432444178112ecd80a104508030de650f9bebe0e7a5","source":{"kind":"arxiv","id":"2507.21809","version":2},"attestation_state":"computed","paper":{"title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Chongqing Zhao, Chunchao Guo, Di Wang, Dongyuan Guo, Haoyuan Wang, Hao Zhang, HunyuanWorld Team, Jiaao Yu, Jianchen Zhu, Jie Jiang, Jie Xiao, Jihong Zhang, Jinbao Xue, Junlin Yu, Junta Wu, Kai Liu, Lei Wang, Liang Dong, Lifu Wang, Lin Niu, Linus, Meng Chen, Minghui Chen, Peng Chen, Peng He, Puhua Jiang, Runzhou Wu, Sheng Zhang, Sicong Liu, Tengfei Wang, Tian Liu, Tianyu Huang, Wangchen Qin, Wenhuan Li, Xianghui Yang, Xiang Yuan, Xiaofeng Yang, Xinming Wu, Xinyue Mao, Xuhui Zuo, Yangyu Tao, Yifu Sun, Yihang Lian, YingPing He, Yiwen Jia, Yixuan Tang, Yonghao Tan, Yuhao Liu, Yuhong Liu, Yulin Tsai, Zhan Li, Zheng Ye, Zhenwei Wang, Zixiao Gu","submitted_at":"2025-07-29T13:43:35Z","abstract_excerpt":"Creating immersive and playable 3D worlds from texts or images remains a fundamental challenge in computer vision and graphics. Existing world generation approaches typically fall into two categories: video-based methods that offer rich diversity but lack 3D consistency and rendering efficiency, and 3D-based methods that provide geometric consistency but struggle with limited training data and memory-inefficient representations. To address these limitations, we present HunyuanWorld 1.0, a novel framework that combines the best of both worlds for generating immersive, explorable, and interactiv"},"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":"2507.21809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T13:43:35Z","cross_cats_sorted":[],"title_canon_sha256":"daeef84085784a6d04241563a0badb2d8a31a5692471f6a500fb6fff6d77c1e2","abstract_canon_sha256":"5416cd81b28a64246fc042af1a1909e56d1f54c18f8d314fd614e7e202f98462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:06.165918Z","signature_b64":"AhN1UovKggewfAGwIUPSYYPd6Ld5Z9xwj1Ilwwauz7m9noDZ+5B7N+FxT/THpUvw8fN7/VvYkt2Yp0uzh/MpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e0fac6e06ff412d52942432444178112ecd80a104508030de650f9bebe0e7a5","last_reissued_at":"2026-07-05T11:53:06.165449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:06.165449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Chongqing Zhao, Chunchao Guo, Di Wang, Dongyuan Guo, Haoyuan Wang, Hao Zhang, HunyuanWorld Team, Jiaao Yu, Jianchen Zhu, Jie Jiang, Jie Xiao, Jihong Zhang, Jinbao Xue, Junlin Yu, Junta Wu, Kai Liu, Lei Wang, Liang Dong, Lifu Wang, Lin Niu, Linus, Meng Chen, Minghui Chen, Peng Chen, Peng He, Puhua Jiang, Runzhou Wu, Sheng Zhang, Sicong Liu, Tengfei Wang, Tian Liu, Tianyu Huang, Wangchen Qin, Wenhuan Li, Xianghui Yang, Xiang Yuan, Xiaofeng Yang, Xinming Wu, Xinyue Mao, Xuhui Zuo, Yangyu Tao, Yifu Sun, Yihang Lian, YingPing He, Yiwen Jia, Yixuan Tang, Yonghao Tan, Yuhao Liu, Yuhong Liu, Yulin Tsai, Zhan Li, Zheng Ye, Zhenwei Wang, Zixiao Gu","submitted_at":"2025-07-29T13:43:35Z","abstract_excerpt":"Creating immersive and playable 3D worlds from texts or images remains a fundamental challenge in computer vision and graphics. Existing world generation approaches typically fall into two categories: video-based methods that offer rich diversity but lack 3D consistency and rendering efficiency, and 3D-based methods that provide geometric consistency but struggle with limited training data and memory-inefficient representations. To address these limitations, we present HunyuanWorld 1.0, a novel framework that combines the best of both worlds for generating immersive, explorable, and interactiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21809","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/2507.21809/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":"2507.21809","created_at":"2026-07-05T11:53:06.165508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21809v2","created_at":"2026-07-05T11:53:06.165508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21809","created_at":"2026-07-05T11:53:06.165508+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYH2Y3QG75AS","created_at":"2026-07-05T11:53:06.165508+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYH2Y3QG75AS2UUU","created_at":"2026-07-05T11:53:06.165508+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYH2Y3QG","created_at":"2026-07-05T11:53:06.165508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":258,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21775","citing_title":"Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18180","citing_title":"EgoCS-400K: An Egocentric Gameplay Dataset for World Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13655","citing_title":"Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13376","citing_title":"MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11529","citing_title":"XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12213","citing_title":"SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360$^\\circ$ Panorama Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31336","citing_title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00499","citing_title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04876","citing_title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07527","citing_title":"From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11911","citing_title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18636","citing_title":"Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21686","citing_title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09535","citing_title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08995","citing_title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18215","citing_title":"Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE","json":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE.json","graph_json":"https://pith.science/api/pith-number/DYH2Y3QG75AS2UUUEQZEIQLYCE/graph.json","events_json":"https://pith.science/api/pith-number/DYH2Y3QG75AS2UUUEQZEIQLYCE/events.json","paper":"https://pith.science/paper/DYH2Y3QG"},"agent_actions":{"view_html":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE","download_json":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE.json","view_paper":"https://pith.science/paper/DYH2Y3QG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21809&json=true","fetch_graph":"https://pith.science/api/pith-number/DYH2Y3QG75AS2UUUEQZEIQLYCE/graph.json","fetch_events":"https://pith.science/api/pith-number/DYH2Y3QG75AS2UUUEQZEIQLYCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE/action/storage_attestation","attest_author":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE/action/author_attestation","sign_citation":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE/action/citation_signature","submit_replication":"https://pith.science/pith/DYH2Y3QG75AS2UUUEQZEIQLYCE/action/replication_record"}},"created_at":"2026-07-05T11:53:06.165508+00:00","updated_at":"2026-07-05T11:53:06.165508+00:00"}