Commentsv3: Minor revision in response to peer review. Methodological and reproducibility refinements across the case studies and the governance section
Comments11 pages, 9 figures. Accepted as a demo paper at ICAIL 2026. This arXiv version includes an appendix, new results, bug fixes, and presentation improvements beyond the earlier preprint; consequently, some reported numbers differ
Roberto Capobianco, Harm van Seijen, Nolan D. Bard, Neil Burch, Fatima Davelouis, Josh Davidson, Alisa Devlic, Yunshu Du, Ishan Durugkar, Siddhant Gangapurwala, Daniel Hernandez, G. Zacharias Holland, Sahil Jain, Kenta Kawamoto, Raksha Kumaraswamy, Patrick MacAlpine, Dustin R. Morrill, Declan Oller, Francesco Riccio, Akanksha Saran, Craig Sherstan, Kaushik Subramanian, Thomas J. Walsh, Samuel Barrett, Kizza N. Frisbee, Mady Govil, Johannes Günther, Varun R. Kompella, James A. MacGlashan, Maxwell Svetlik, Michael D. Thomure, Jaden B. Travnik, Kevin Waugh, Elahe Aghapour, Florian Fuchs, Andreanne Lemay, Shruti Mishra, Takuma Seno, Peter Stone, Michael Spranger, Peter R. Wurman
机构
*
Sony AI, Zurich, Switzerland(索尼AI,苏黎世,瑞士)
;
Sony AI, North America (various locations)(索尼AI,北美(多地))
;
Sony AI, Tokyo, Japan(索尼AI,东京,日本)
David Bonet, Marçal Comajoan Cara, Alvaro Calafell, Daniel Mas Montserrat, Alexander G. Ioannidis
机构
*
Stanford University(斯坦福大学)
;
University of California, Santa Cruz(加州大学圣克鲁兹分校)
;
University of California, Berkeley(加州大学伯克利分校)
;
École Polytechnique(巴黎高等理工学院)
When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero
AlphaZero-Edu:普及AlphaZero的访问
Ruitong Li, Binjie Guo, Aisheng Mo, Guowei Su, Han Wang, Jie Li, Ru Zhang
机构
*
Department of Communication Studies, School of Communication, Hong Kong Baptist University(通讯学院传播研究系,香港 Baptist 大学)
;
Department of Neurobiology and Department of Rehabilitation Medicine, First Affiliated Hospital, Zhejiang University School of Medicine(神经生物学系和康复医学系,浙江大学医学院第一附属医院)
;
Personal participation(个人参与)
Comments11 pages, 3 figures. v4: retitled; adds a dataset-by-representation interaction test (+0.097, 95% CI [+0.032,+0.160], p=0.001) and seed stability for both datasets, replacing the earlier claim that both within-dataset intervals excluded zero (the Memento10k bound was -0.0003); discloses that the pre-specified hypothesis returned NO-GO; adds a regularization-grid check
Lorenz Hufe, Niclas Griesshaber, Gavin Greif, Sebastian Oliver Eck, Philip Torr
机构
*
Torr Vision Group, Department of Engineering Science, University of Oxford(牛津大学工程科学系托尔视觉组)
;
Oxford Centre for Economic and Social History, University of Oxford(牛津大学牛津经济与社会史中心)
;
Faculty of Music, University of Oxford(牛津大学音乐学院)
;
Fraunhofer HHI(弗劳恩霍夫海因里希·赫兹研究所)
机构
*
School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院)
;
Department of Health Technology and Informatics, and Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University(香港理工大学健康科技与信息学系、数据科学与人工智能系)