{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:57:36Z","timestamp":1776931056257,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S023917\/1"],"award-info":[{"award-number":["EP\/S023917\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3742413.3789226","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T11:32:24Z","timestamp":1772537544000},"page":"474-488","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Explanations: A Quantitative Model of Human Error in Causal Graph Interpretation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8904-6387","authenticated-orcid":false,"given":"Paul-David","family":"Zuercher","sequence":"first","affiliation":[{"name":"University of Cambridge, Cambridge, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5986-8638","authenticated-orcid":false,"given":"Thomas","family":"Bohn\u00e9","sequence":"additional","affiliation":[{"name":"Cyber-Human Lab, University of Cambridge, Cambridge, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7139-871X","authenticated-orcid":false,"given":"Per Ola","family":"Kristensson","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Cambridge, Cambridge, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Virginia Aglietti Xiaoyu Lu Andrei Paleyes and Javier Gonz\u00e1lez. [n. d.]. Causal Bayesian Optimization. ([n. d.])."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"I Baaj Z Bouraoui A Cornu\u00e9jols T Den\u00e6ux S Destercke D Dubois MJ Lesot J Marques-Silva J Mengin H Prade S Schockaert M Serrurier O Strauss and C Vrain. 2024. Synergies between machine learning and reasoningAn introduction by the Kay R. Amel group. 171 (2024). 10.1016\/j.ijar.2024.109206","DOI":"10.1016\/j.ijar.2024.109206"},{"key":"e_1_3_3_3_4_2","unstructured":"Elias Bareinboim Juan\u00a0D Correa Duligur Ibeling and Thomas Icard. [n. d.]. 1 On Pearl\u2019s Hierarchy and the Foundations of Causal Inference. ([n. d.])."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Jonathan Barnes. 1994. Posterior analytics. (1994).","DOI":"10.1049\/ee.1994.0001"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1358628.1358747"},{"key":"e_1_3_3_3_7_2","unstructured":"Shriya Bhatija Paul-David Zuercher Jakob Thumm and Thomas Bohn\u00e9. 2025. Multi-Objective Causal Bayesian Optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.14755 (2025)."},{"key":"e_1_3_3_3_8_2","unstructured":"Matthew Britton. 2019. Vine: Visualizing statistical interactions in black box models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.00561 (2019)."},{"key":"e_1_3_3_3_9_2","unstructured":"Ian Covert Scott Lundberg and Su-In Lee. 2020. Feature removal is a unifying principle for model explanation methods. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2011.03623 (2020)."},{"key":"e_1_3_3_3_10_2","unstructured":"Ian Covert Scott Lundberg and Su-In Lee. 2021. Explaining by removing: A unified framework for model explanation. Journal of Machine Learning Research 22 209 (2021) 1\u201390."},{"key":"e_1_3_3_3_11_2","unstructured":"Lisa Ehrlinger and Wolfram W\u00f6\u00df. [n. d.]. Towards a De\ufb01nition of Knowledge Graphs. ([n. d.])."},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Churchill Eisenhart. 1947. The assumptions underlying the analysis of variance. Biometrics 3 1 (1947) 1\u201321.","DOI":"10.2307\/3001534"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Graeme\u00a0S Halford William\u00a0H Wilson and Steven Phillips. 1998. Processing capacity defined by relational complexity: Implications for comparative developmental and cognitive psychology. Behavioral and brain sciences 21 6 (1998) 803\u2013831.","DOI":"10.1017\/S0140525X98001769"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"A. Holzinger B. Malle A. Saranti and B. Pfeifer. 2021. Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI. 71 (2021) 28\u201337. 10.1016\/j.inffus.2021.01.008","DOI":"10.1016\/j.inffus.2021.01.008"},{"key":"e_1_3_3_3_15_2","unstructured":"Joseph\u00a0A Konstan Ed Chi and Kristina H\u00f6\u00f6k. 2012. Proceedings of the SIGCHI conference on human factors in computing systems. ACM Press."},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"crossref","unstructured":"William\u00a0H Kruskal and W\u00a0Allen Wallis. 1952. Use of ranks in one-criterion variance analysis. Journal of the American statistical Association 47 260 (1952) 583\u2013621.","DOI":"10.1080\/01621459.1952.10483441"},{"key":"e_1_3_3_3_17_2","unstructured":"Sanghack Lee and Elias Bareinboim. 2020. Characterizing optimal mixed policies: Where to intervene and what to observe. Advances in neural information processing systems 33 (2020) 8565\u20138576."},{"key":"e_1_3_3_3_18_2","volume-title":"Testing statistical hypotheses","author":"Lehmann Erich\u00a0L","year":"2006","unstructured":"Erich\u00a0L Lehmann and Joseph\u00a0P Romano. 2006. Testing statistical hypotheses. Springer Science & Business Media."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Zipeng Liu Takayuki Itoh Jessica\u00a0Q Dawson and Tamara Munzner. 2020. The sprawlter graph readability metric: Combining sprawl and area-aware clutter. IEEE Transactions on Visualization and Computer Graphics 26 6 (2020) 2180\u20132191.","DOI":"10.1109\/TVCG.2020.2970523"},{"key":"e_1_3_3_3_20_2","unstructured":"Dongsheng Luo Wei Cheng Dongkuan Xu Wenchao Yu Bo Zong Haifeng Chen and Xiang Zhang. 2020. Parameterized explainer for graph neural network. Advances in neural information processing systems 33 (2020) 19620\u201319631."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Kim Marriott Helen Purchase Michael Wybrow and Cagatay Goncu. 2012. Memorability of visual features in network diagrams. IEEE Transactions on Visualization and Computer Graphics 18 12 (2012) 2477\u20132485.","DOI":"10.1109\/TVCG.2012.245"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"crossref","unstructured":"Andrea Mastropietro Giuseppe Pasculli Christian Feldmann Raquel Rodr\u00edguez-P\u00e9rez and J\u00fcrgen Bajorath. 2022. EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks. Iscience 25 10 (2022).","DOI":"10.1016\/j.isci.2022.105043"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Cathleen McGrath Jim Blythe and David Krackhardt. 1997. The effect of spatial arrangement on judgments and errors in interpreting graphs. Social networks 19 3 (1997) 223\u2013242.","DOI":"10.1016\/S0378-8733(96)00299-7"},{"key":"e_1_3_3_3_24_2","first-page":"13","volume-title":"DS 58-6: Proceedings of ICED 09, the 17th International Conference on Engineering Design, Vol. 6, Design Methods and Tools (pt. 2), Palo Alto, CA, USA, 24.-27.08. 2009","author":"Miyashita Tomoyuki","year":"2009","unstructured":"Tomoyuki Miyashita, Daisuke Satoh, et\u00a0al. 2009. A direction of ideas in conceptual design using data envelopment analysis. In DS 58-6: Proceedings of ICED 09, the 17th International Conference on Engineering Design, Vol. 6, Design Methods and Tools (pt. 2), Palo Alto, CA, USA, 24.-27.08. 2009. 13\u201322."},{"key":"e_1_3_3_3_25_2","unstructured":"Christoph Molnar Gunnar K\u00f6nig Bernd Bischl and Giuseppe Casalicchio. 2023. Model-agnostic feature importance and effects with dependent features: a conditional subgroup approach. Data Mining and Knowledge Discovery (2023) 1\u201339."},{"key":"e_1_3_3_3_26_2","volume-title":"Design and analysis of experiments","author":"Montgomery Douglas\u00a0C","year":"2017","unstructured":"Douglas\u00a0C Montgomery. 2017. Design and analysis of experiments. John wiley & sons."},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Takafumi Nakanishi. 2023. Approximate inverse model explanations (AIME): unveiling local and global insights in machine learning models. IEEE Access (2023).","DOI":"10.1109\/ACCESS.2023.3314336"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445315"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"A. Rawal A. Raglin B.M. Sadler and D.B. Rawat. 2023. Explainability and causality for robust fair and trustworthy artificial reasoning Vol.\u00a012538. 10.1117\/12.2666085","DOI":"10.1117\/12.2666085"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"A. Rawal A. Raglin Q. Wang and Z. Tang. 2024. A Comparison of Causal Discovery and Explainable AI (XAI) for Image Datasets Vol.\u00a013051. 10.1117\/12.3013193","DOI":"10.1117\/12.3013193"},{"key":"e_1_3_3_3_31_2","unstructured":"E. Reiter. 2019. Natural language generation challenges for explainable AI. 3\u20137. https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-85090501598&partnerID=40&md5=8ad8cdaab68b413a46ac8e49ba6c4585"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Thomas Schnake Oliver Eberle Jonas Lederer Shinichi Nakajima Kristof\u00a0T Sch\u00fctt Klaus-Robert M\u00fcller and Gr\u00e9goire Montavon. 2021. Higher-order explanations of graph neural networks via relevant walks. IEEE transactions on pattern analysis and machine intelligence 44 11 (2021) 7581\u20137596.","DOI":"10.1109\/TPAMI.2021.3115452"},{"key":"e_1_3_3_3_34_2","unstructured":"M Scott Lee Su-In et\u00a0al. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017) 4765\u20134774."},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173806"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534639"},{"key":"e_1_3_3_3_37_2","unstructured":"Sahil Verma Varich Boonsanong Minh Hoang Keegan Hines John Dickerson and Chirag Shah. 2020. Counterfactual explanations and algorithmic recourses for machine learning: A review. Comput. Surveys (2020)."},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533170"},{"key":"e_1_3_3_3_39_2","first-page":"37091","volume-title":"International Conference on Machine Learning","author":"Wilming Rick","year":"2023","unstructured":"Rick Wilming, Leo Kieslich, Benedict Clark, and Stefan Haufe. 2023. Theoretical behavior of XAI methods in the presence of suppressor variables. In International Conference on Machine Learning. PMLR, 37091\u201337107."},{"key":"e_1_3_3_3_40_2","unstructured":"Ziyuan Ye Rihan Huang Qilin Wu and Quanying Liu. 2024. Same: Uncovering GNN black box with structure-aware Shapley-based multipiece explanations. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_3_41_2","unstructured":"Chih-Kuan Yeh Cheng-Yu Hsieh Arun Suggala David\u00a0I Inouye and Pradeep\u00a0K Ravikumar. 2019. On the (in) fidelity and sensitivity of explanations. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_3_42_2","unstructured":"Zhitao Ying Dylan Bourgeois Jiaxuan You Marinka Zitnik and Jure Leskovec. 2019. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"crossref","unstructured":"Chi Zhao Jing Liu and Elena Parilina. 2025. ShapG: new feature importance method based on the Shapley value. Engineering Applications of Artificial Intelligence 148 (2025) 110409.","DOI":"10.1016\/j.engappai.2025.110409"}],"event":{"name":"IUI '26: 31st International Conference on Intelligent User Interfaces","location":"Paphos Cyprus","acronym":"IUI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 31st International Conference on Intelligent User Interfaces"],"original-title":[],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T13:02:13Z","timestamp":1773493333000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742413.3789226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":42,"alternative-id":["10.1145\/3742413.3789226","10.1145\/3742413"],"URL":"https:\/\/doi.org\/10.1145\/3742413.3789226","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}