[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125478-en":3,"doc-seo-125478-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125478,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Understanding with Toy Surrogate Models in Machine Learning","Toy models—extremely simple, highly idealized representations—are widely used in natural and social sciences to illuminate complex phenomena. Surrogate models in explainable AI often resemble these scientific tools, but a key difference remains: the target of a surrogate is another model rather than a real-world system. The paper develops an account of what global understanding of an opaque machine learning model means when achieved through toy surrogate models, clarifying their epistemic function and limits.","Accepted for publication in Minds and Machines. Please quote the printed version.  \nUnderstanding with Toy Surrogate Models in Machine Learning  \nAndrés Páez  \nUniversidad de los Andes  \nABSTRACT  \nIn the natural and social sciences, it is common to use toy models—extremely simple and highly idealized representations—to understand complex phenomena. Some of the simple surrogate models used to understand opaque machine learning (ML) models, such as rule lists and sparse decision trees, bear some resemblance to scientific toy models. They allow non-experts to understand how an opaque ML model works globally via a much simpler model that highlights the most relevant features of the input space and their effect on the output. The obvious difference is that the common target of a toy and a full-scale model in the sciences is some phenomenon in the world, while the target of a surrogate model is another model. This essential difference makes toy surrogate models (TSMs) a new object of study for theories of understanding, one that is not easily accommodated under current analyses. This paper provides an account of what it means to understand an opaque ML model globally with the aid of such simple models.  \nKeywords: Toy models, Surrogate models, Machine learning, Understanding, Idealization  \n1. Introduction  \nIn the natural and social sciences, it is common to use extremely simple and highly idealized models to understand complex phenomena. Unlike regular models, these very simple models—often referred to as toy models—are not required to be linked to the real world through structural similarity or resemblance relations. They are not meant to be approximations ofthe target world system, and in some cases, they are not even required to be representational. In semantic terms, they do not accurately map onto their targets. Despite these limitations, they are still useful in understanding theoretical concepts and possible configurations of the target system. Paradigmatic examples of toy models include Boyle’s law and the Ising model in physics, the Lotka–Volterra model in population ecology, and the Schelling model in the social sciences (Weisberg, 2013) .  \nIn recent years, philosophers of science have become interested in toy models (Grüne-Yanoff, 2009; Luczak, 2017; Reutlinger et al., 2018; Frigg & Nguyen, 2017; Nguyen, 2020) . The main purpose of this literature is to explore the nature of these models and examine how they perform their epistemic function. Despite lacking the regular descriptive and predictive features of full-scale scientific models, they often offer an elementary understanding of a phenomenon. Their definitions of “toy model” differ as well as their assessment of the importance of representation in modelling generally, but they all agree that toy models play an important epistemic role in scientific research, exploration, and pedagogy.  \nPrima facie, some of the proxy, interpretative, approximate, or surrogate models1 used in explainable AI (XAI) to make sense of black box machine learning (ML) systems play an analogous role to toy models in the sciences.2 In both cases, the models fulfill what Frigg and Nguyen (2020, p. 3), following Swoyer (1991), call the surrogative reasoning condition for representation: models represent in a way that allows scientists or users to make inferences about the models’ target systems; they can generate claims about target systems by investigating models that represent them. Although many surrogate models used by developers in ML are black boxes,3 the simplest of them—e.g., rule lists and sparse decision trees—allow non-experts to understand how an opaque ML model works globally via a much simpler model that highlights the most relevant features of the input space and their effect on the output. Toy surrogate models (TSMs), as I will call them, only work when the system’s features can be interpreted semantically, that is, when they represent recognizable elements of the user’s envi","cbCaimVdJWkqR6kd","https://ap.wps.com/l/cbCaimVdJWkqR6kd","pdf",472495,1,38,"English","en",105,"# Introduction\n## Toy models in science\n## Surrogative reasoning in explainable AI\n## Toy surrogate models and global understanding","[{\"question\":\"What problem do toy surrogate models address in machine learning?\",\"answer\":\"They aim to explain how an opaque machine learning model behaves globally by using a much simpler model that highlights relevant input features and their effects on output.\"},{\"question\":\"How is a toy model in science different from a toy surrogate model in machine learning?\",\"answer\":\"In science, toy and full-scale models target a real-world phenomenon, while in ML the surrogate model targets another model rather than the world itself.\"},{\"question\":\"When do toy surrogate models work best?\",\"answer\":\"They work when the model features can be interpreted semantically, so the surrogate captures recognizable elements in the user’s environment.\"}]","Understanding with Toy Surrogate Models in Machine Learning | PDF",1785899220,96,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"understanding-with-toy-surrogate-models-in-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/understanding-with-toy-surrogate-models-in-machine-learning/125478/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem do toy surrogate models address in machine learning?","Question",{"text":75,"@type":76},"They aim to explain how an opaque machine learning model behaves globally by using a much simpler model that highlights relevant input features and their effects on output.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is a toy model in science different from a toy surrogate model in machine learning?",{"text":80,"@type":76},"In science, toy and full-scale models target a real-world phenomenon, while in ML the surrogate model targets another model rather than the world itself.",{"name":82,"@type":73,"acceptedAnswer":83},"When do toy surrogate models work best?",{"text":84,"@type":76},"They work when the model features can be interpreted semantically, so the surrogate captures recognizable elements in the user’s environment.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]