{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:13Z","timestamp":1786120813205,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Foundation, Singapore under its AI Singapore Programme","award":["AISG-NMLP-2024-003"],"award-info":[{"award-number":["AISG-NMLP-2024-003"]}]},{"name":"National Research Foundation, Singa- pore and Infocomm Media Development Authority under its Trust Tech Funding Initiative,","award":["DTC-RGC-05"],"award-info":[{"award-number":["DTC-RGC-05"]}]},{"name":"ational Research Foundation, Singapore under its Smart Nation & Digital Government Transla- tional R&D Grant (TRANS)","award":["RANS2023-TGC03"],"award-info":[{"award-number":["RANS2023-TGC03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817582","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"9848-9859","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-2492","authenticated-orcid":false,"given":"Tianyi","family":"Tang","sequence":"first","affiliation":[{"name":"CFAR, IHPC, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4942-160X","authenticated-orcid":false,"given":"Zhuoyi","family":"Lin","sequence":"additional","affiliation":[{"name":"I2R, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6069-7060","authenticated-orcid":false,"given":"Zeyu","family":"Feng","sequence":"additional","affiliation":[{"name":"CFAR, IHPC, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9123-8827","authenticated-orcid":false,"given":"Tianyi","family":"Ma","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore and CFAR, IHPC, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore and CFAR, IHPC, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8095-4637","authenticated-orcid":false,"given":"Ivor","family":"Tsang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore and CFAR, IHPC, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9576-9398","authenticated-orcid":false,"given":"Haiyan","family":"Yin","sequence":"additional","affiliation":[{"name":"CFAR, IHPC, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Marah Abdin et al. 2024. Phi-4 Technical Report. arXiv:2412.08905 [cs.CL] https:\/\/arxiv.org\/abs\/2412.08905"},{"key":"e_1_3_2_1_2_1","unstructured":"Anthropic. 2025. Introducing Claude 4. https:\/\/www.anthropic.com\/news\/claude-4. Accessed: 2025-09-25."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE international conference on computer vision. 2425-2433","author":"Stanislaw","unstructured":"Stanislaw Antol et al., 2015. Vqa: Visual question answering. In Proceedings of the IEEE international conference on computer vision. 2425-2433."},{"key":"e_1_3_2_1_4_1","unstructured":"Samuel Ayman. [n.d.]. Cup Dataset [Kaggle]. Accessed: 2025-11-21."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Alisson Azzolini et al. 2025. Cosmos-reason1: From physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558 (2025).","DOI":"10.70777\/si.v2i4.15315"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks).","author":"Daniel","unstructured":"Daniel M Bear et al., 2021. Physion: Evaluating Physical Prediction from Vision in Humans and Machines. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1207\/S15327647JCD0101N_3"},{"key":"e_1_3_2_1_8_1","volume-title":"European conference on computer vision. Springer, 213-229","author":"Nicolas","unstructured":"Nicolas Carion et al., 2020. End-to-end object detection with transformers. In European conference on computer vision. Springer, 213-229."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1247"},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Zhenfang","unstructured":"Zhenfang Chen et al., 2022. ComPhy: Compositional Physical Reasoning of Objects and Events from Videos. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_11_1","volume-title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding. In International Conference on Learning Representations (ICLR).","author":"Wei","unstructured":"Wei Chow et al., 2025. PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_12_1","unstructured":"Gheorghe Comanici et al. 2025. Gemini 2.5: Pushing the Frontier with Advanced Reasoning Multimodality Long Context and Next Generation Agentic Capabilities. arXiv:2507.06261 [cs.CL] https:\/\/arxiv.org\/abs\/2507.06261"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00910"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"e_1_3_2_1_15_1","volume-title":"Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT. arXiv preprint arXiv:2505.24182","author":"Zhuobai Dong","year":"2025","unstructured":"Zhuobai Dong et al., 2025. Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT. arXiv preprint arXiv:2505.24182 (2025)."},{"key":"e_1_3_2_1_16_1","unstructured":"Aaron Foss et al. 2025. CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models. arXiv preprint arXiv:2506.09943 (2025)."},{"key":"e_1_3_2_1_17_1","unstructured":"Jiarun Fu et al. 2025. Unveiling and causalizing cot: A causal pespective. arXiv preprint arXiv:2502.18239 (2025)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_2_1_19_1","unstructured":"Aaron Grattafiori et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Kristen Grauman et al. 2025. Ego4D: Around the World in 3 600 Hours of Egocentric Video. IEEE Trans. Pattern Anal. Mach. Intell. V47 11 (2025) 9468-9509. doi:10.1109\/TPAMI.2024.3381075","DOI":"10.1109\/TPAMI.2024.3381075"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Agrim Gupta et al. 2021. Embodied intelligence via learning and evolution. Nature communications V12 1 (2021) 5721.","DOI":"10.1038\/s41467-021-25874-z"},{"key":"e_1_3_2_1_22_1","unstructured":"Victor-Louis De Gusseme et al. 2025. A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition. arXiv:2508.16749 [cs.RO] https:\/\/arxiv.org\/abs\/2508.16749"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (ICML).","author":"Yunzhuo","unstructured":"Yunzhuo Hao et al., 2025. Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal Reasoning Benchmark. In Proceedings of the 42nd International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.211"},{"key":"e_1_3_2_1_25_1","unstructured":"Aaron Hurst et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Visscience: An extensive benchmark for evaluating k12 educational multi-modal scientific reasoning. arXiv preprint arXiv:2409.13730","author":"Zhihuan Jiang","year":"2024","unstructured":"Zhihuan Jiang et al., 2024. Visscience: An extensive benchmark for evaluating k12 educational multi-modal scientific reasoning. arXiv preprint arXiv:2409.13730 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Cladder: Assessing causal reasoning in language models. Advances in Neural Information Processing Systems, V36","author":"Zhijing Jin","year":"2023","unstructured":"Zhijing Jin et al., 2023. Cladder: Assessing causal reasoning in language models. Advances in Neural Information Processing Systems, V36 (2023), 31038-31065."},{"key":"e_1_3_2_1_28_1","unstructured":"Thomas Jiralerspong et al. 2024. Efficient causal graph discovery using large language models. arXiv preprint arXiv:2402.01207 (2024)."},{"key":"e_1_3_2_1_29_1","unstructured":"Kantine. [n.d.]. DOMOTIC PouringCoffee Expert Dataset [Hugging Face]. Accessed: 2025-11-20."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1561"},{"key":"e_1_3_2_1_31_1","unstructured":"Ville Kuosmanen. [n.d.]. AGILEX Clean Pour Water Dataset [Hugging Face]. Accessed: 2025-11-20."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Junnan","unstructured":"Junnan Li et al., 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR","author":"Junnan","unstructured":"Junnan Li et al., 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_34_1","unstructured":"Jianing Li et al. 2024. Proximity qa: Unleashing the power of multi-modal large language models for spatial proximity analysis. arXiv preprint arXiv:2401.17862 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.288"},{"key":"e_1_3_2_1_36_1","unstructured":"Disheng Liu et al. 2025. Causal3d: A comprehensive benchmark for causal learning from visual data. arXiv preprint arXiv:2503.04852 (2025)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Pan Lu et al. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems V35 (2022) 2507-2521.","DOI":"10.52202\/068431-0182"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.9.4.636"},{"key":"e_1_3_2_1_39_1","volume-title":"Nexar Dashcam Collision Prediction Dataset and Challenge. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Computer Vision Foundation \/ IEEE, 2583-2591","author":"Daniel","unstructured":"Daniel C. Moura et al., 2025. Nexar Dashcam Collision Prediction Dataset and Challenge. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Computer Vision Foundation \/ IEEE, 2583-2591."},{"key":"e_1_3_2_1_40_1","unstructured":"OpenAI et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_41_1","unstructured":"Judea Pearl. 2009. Causality. Cambridge university press."},{"key":"e_1_3_2_1_42_1","unstructured":"Qwen et al. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on machine learning. PmLR.","author":"Alec","unstructured":"Alec Radford et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR."},{"key":"e_1_3_2_1_44_1","unstructured":"Goutham Rajendran et al. 2024. Learning interpretable concepts: Unifying causal representation learning and foundation models. arXiv preprint arXiv:2402.09236 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1195"},{"key":"e_1_3_2_1_46_1","volume-title":"Conference on robot learning. PMLR, 477-490","author":"Sanjana","unstructured":"Sanjana Srivastava et al., 2022. Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments. In Conference on robot learning. PMLR, 477-490."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Mistral AI Team. 2025. Mistral Small 3: Apache 2.0 81% MMLU 150 tokens\/s. https:\/\/mistral.ai\/news\/mistral-small-3. Accessed: 2025-09-25.","DOI":"10.5840\/mr2025315"},{"key":"e_1_3_2_1_48_1","volume-title":"Physion: Evaluating physical scene understanding that requires online inference of different physical properties. Advances in Neural Information Processing Systems, V36","author":"Tung Hsiao-Yu","year":"2023","unstructured":"Hsiao-Yu Tung et al., 2023. Physion: Evaluating physical scene understanding that requires online inference of different physical properties. Advances in Neural Information Processing Systems, V36 (2023), 67048-67068."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 19757-19767","author":"Tai","unstructured":"Tai Wang et al., 2024. Embodiedscan: A holistic multi-modal 3d perception suite towards embodied ai. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 19757-19767."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Qi Wu et al. 2017. Visual question answering: A survey of methods and datasets. Computer Vision and Image Understanding V163 (2017) 21-40.","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"e_1_3_2_1_51_1","unstructured":"An Yang et al. 2024. Qwen2 Technical Report. arXiv:2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_52_1","unstructured":"An Yang et al. 2025a. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference. 10632-10643","author":"Jihan","unstructured":"Jihan Yang et al., 2025b. Thinking in space: How multimodal large language models see, remember, and recall spaces. In Proceedings of the Computer Vision and Pattern Recognition Conference. 10632-10643."},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 8809-8818","author":"Yang Xin","unstructured":"Xin Yang, Haiyang Mei, Ke Xu, Xiaopeng Wei, Baocai Yin, and Rynson W. H. Lau. 2019. Where Is My Mirror?. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 8809-8818."},{"key":"e_1_3_2_1_55_1","volume-title":"CLEVRER: Collision Events for Video Representation and Reasoning. In International Conference on Learning Representations (ICLR).","author":"Kexin","unstructured":"Kexin Yi et al., 2020. CLEVRER: Collision Events for Video Representation and Reasoning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","unstructured":"Baiqiao Yin et al. 2025. Spatial Mental Modeling from Limited Views. CoRR Vabs\/2506.21458 (2025). arXiv:2506.21458 doi:10.48550\/ARXIV.2506.21458","DOI":"10.48550\/ARXIV.2506.21458"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.811"},{"key":"e_1_3_2_1_58_1","unstructured":"Jinguo Zhu et al. 2025. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv:2504.10479 [cs.CV] https:\/\/arxiv.org\/abs\/2504.10479"},{"key":"e_1_3_2_1_59_1","unstructured":"Mingwei Zhu et al. 2023. Benchmarking sequential visual input reasoning and prediction in multimodal large language models. arXiv preprint arXiv:2310.13473 (2023)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:29:15Z","timestamp":1786066155000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817582"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":59,"alternative-id":["10.1145\/3770855.3817582","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817582","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}