{"paper":{"title":"Advancing Open-source World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LingBot-World is an open-source world simulator from video generation that claims high fidelity across environments, minute-scale temporal consistency, and sub-second latency at 16 frames per second.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanlin Wang, Hao Ouyang, Jiapeng Zhu, Jiayi Zhu, Jie Liu, Jingye Chen, Ka Leong Cheng, Kecheng Zheng, Qingyan Bai, Qiuyu Wang, Robbyant Team: Zelin Gao, Shuailei Ma, Xing Zhu, Yanhong Zeng, Yansong Cheng, Yao Yao, Yihang Chen, Yihao Meng, Yinghao Xu, Yixuan Li, Yue Yu, Yujun Shen, Zehong Shen","submitted_at":"2026-01-28T12:37:01Z","abstract_excerpt":"We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as \"long-term memory\". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public acces"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as 'long-term memory'. (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the released model actually achieves the stated levels of fidelity, minute-scale consistency, and sub-second latency across diverse environments, as the abstract provides no benchmarks, comparisons, or implementation details to support these performance assertions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LingBot-World is presented as an open-source world model that delivers high-fidelity simulation, minute-level contextual consistency, and real-time interactivity under one second latency.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LingBot-World is an open-source world simulator from video generation that claims high fidelity across environments, minute-scale temporal consistency, and sub-second latency at 16 frames per second.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6c0d89bff1ef1ec2f4c7a4c82b9ed433f705778ab7bc5c55ce5bd2a06a28d6f6"},"source":{"id":"2601.20540","kind":"arxiv","version":1},"verdict":{"id":"13a3d94a-706b-43fb-9681-15e1d9735669","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:02:34.641612Z","strongest_claim":"Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as 'long-term memory'. (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second.","one_line_summary":"LingBot-World is presented as an open-source world model that delivers high-fidelity simulation, minute-level contextual consistency, and real-time interactivity under one second latency.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the released model actually achieves the stated levels of fidelity, minute-scale consistency, and sub-second latency across diverse environments, as the abstract provides no benchmarks, comparisons, or implementation details to support these performance assertions.","pith_extraction_headline":"LingBot-World is an open-source world simulator from video generation that claims high fidelity across environments, minute-scale temporal consistency, and sub-second latency at 16 frames per second."},"references":{"count":92,"sample":[{"doi":"","year":2024,"title":"Diffusion for world modeling: Visual details matter in atari","work_id":"981f9f8f-23a1-43b6-b3a0-7985c1de3adf","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","work_id":"a9c28401-f16a-4933-89f0-788e2f94e52b","ref_index":2,"cited_arxiv_id":"2506.09985","is_internal_anchor":true},{"doi":"","year":2025,"title":"Scaling instruction-based video editing with a high-quality synthetic dataset","work_id":"4db310ce-4ba1-4e8d-93a6-90134f0ff4e8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"990d77ea-f62a-4107-9b3c-0d0dfb5b355c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Philip J. Ball, Jakob Bauer, Frank Belletti, Bethanie Brownfield, Ariel Ephrat, Shlomi Fruchter, Agrim Gupta, Kristian Holsheimer, Aleksander Holynski, Jiri Hron, Christos Kaplanis, Marjorie Limont, M","work_id":"fb735614-5ca1-448c-b17c-b9dde7a72be9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":92,"snapshot_sha256":"8171259952c32e560004c2a558534df781de8fc596fb7ec0d2f85535fb170a48","internal_anchors":34},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d3caeb89f497cc9e0fa7dfd0446443149eaf6ced7c6845a254b91497ddf7e015"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}