[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81696-en":3,"doc-seo-81696-105":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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81696,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Bounded Morality: Defining the Space of Moral Computation","Moral cognition is often formalized by fixed ethical theories such as deontology, consequentialism, and virtue ethics, implemented as static rules or value functions. Bounded Morality proposes a formal framework for finite agents that analyzes the computational demands of moral problems. Extending bounded rationality, it defines moral situations using moral breadth and moral depth, revealing a feasible space constrained by limited resources. Within this space, ethical theories act as locally efficient strategies. The framework introduces moral regret and moral progress under constraint and links AI moral alignment to allocated reasoning capacity rather than direct human imitation.","arXiv :2607 .00002v 1 [ cs .AI] 1 Apr 2026  \nBounded Morality  \nDefining the Space of Moral Computation  \nMax Kanwal1,∗,†, Caryn Tran2,† and Patrick Mineault3  \n1 Stanford University 2Northwestern University 3 Amaranth Foundation  \nAbstract  \nMoral cognition has traditionally been modeled as adherence to fixed ethical theories—deontology, consequentialism, virtue ethics—implemented as static rules or value functions. We propose Bounded Morality, a formal framework for analyzing the computational demands of moral problems faced by finite agents. Extending Herbert Simon’s notion of bounded rationality, we formalize moral situations along two orthogonal dimensions: moral breadth, the scope of entities treated as morally relevant, and moral depth, the inferential integration required to evaluate their interactions. Limited resources impose an unavoidable tradeoff between these dimensions, defining a feasible space of moral computation. Within this space, ethical theories correspond to locally efficient strategies adapted to different demand regimes rather than competing accounts of moral truth. The framework yields a formal notion of moral regret and moral progress under constraint, and implies that moral alignment in artificial systems depends on the scaling and allocation of moral reasoning capacity rather than on direct imitation of human judgments.  \nKeywords  \nbounded rationality, resource rationality, moral agents, ethical theories, AI alignment, moral progress  \n“Human rational behavior is shaped by a scissors whose two blades are the structure of the task environment and the computational capabilities of the actor.”  \n—Herbert A. Simon  \n1. Introduction  \nMost attempts to formalize morality in artificial systems proceed by encoding one or more established ethical theories—utilitarian, deontological, contractualist, or virtue-based—into algorithmic decision rules [1, 2, 3, 4] . This strategy treats moral disagreement as a problem of theory selection: the central task is to identify which moral principles an agent ought to implement [5] . While this approach specifies what actions are morally preferred for some situations, it is often not generalizable because it leaves largely unexamined how moral reasoning itself is carried out, how it scales with cognitive capacity, and why distinct moral theories recur across cultures and historical periods.  \nA complementary line of work spanning bounded rationality, rational analysis, and resourcerational cognition has shown that human judgment reflects adaptive trade-offs under computational constraint [6, 7, 8] . Moral cognition has increasingly been analyzed through this lens [9], including within AI alignment research [10] . Related work on bounded ethicality examines how moral behavior  \nAAAI- 26 Workshop on Machine Ethics: from formal methods to emergent machine ethics, January 27, 2026, Singapore  \n∗ Corresponding author.  \n†  \nThese authors contributed equally.  \n£ [kanwal@stanford.edu](kanwal@stanford.edu) (M. Kanwal); [caryn@u.northwestern.edu](caryn@u.northwestern.edu) (C. Tran); [patrick.mineault@gmail.com](patrick.mineault@gmail.com) (P. Mineault)  \nç [https://linkedin.com/in/mkanwal/](https://linkedin.com/in/mkanwal/) (M. Kanwal); [https://linkedin.com/in/caryntran/](https://linkedin.com/in/caryntran/) (C. Tran);  \n[https://www.linkedin.com/in/pmineault/](https://www.linkedin.com/in/pmineault/) (P. Mineault)  \nȈ 0009-0008-7021-3227 (M. Kanwal); 0000-0002-4645-6607 (C. Tran); 0000-0001-5519-842X (P. Mineault)  \n © 2026 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) .  \nis systematically shaped or distorted by cognitive and situational constraints [11, 12] . Together, these traditions describe the limits of moral agents and the strategies they use to cope with those limits. What remains underspecified is the demand side of moral reasoning. That is, which features of moral situations impose the ","cbCaiiz0KY21Cc9M","https://ap.wps.com/l/cbCaiiz0KY21Cc9M","pdf",283090,4,1,24,"English","en",105,"# Abstract\n# Introduction\n# Overview","[{\"question\":\"What problem does Bounded Morality address in modeling moral cognition for AI?\",\"answer\":\"It addresses the gap left by approaches that encode a specific ethical theory but do not explain how moral reasoning is computed, how it scales with cognitive capacity, or why theories recur across contexts. Bounded Morality instead characterizes the computational demands imposed by moral problem structure.\"},{\"question\":\"How does the framework define the space of moral computation?\",\"answer\":\"It uses two orthogonal dimensions: moral breadth (how many entities/groups/timescales are morally relevant) and moral depth (how much inference and information integration is required to evaluate their interactions). Limited resources create unavoidable trade-offs across these dimensions.\"},{\"question\":\"What does Bounded Morality imply about moral regret, moral progress, and AI alignment?\",\"answer\":\"It yields formal notions of moral regret and moral progress under constraint. For artificial systems, moral alignment depends on how moral reasoning capacity is scaled and allocated, rather than on direct imitation of human judgments.\"}]",1784175474,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"bounded-morality-defining-the-space-of-moral-computation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/bounded-morality-defining-the-space-of-moral-computation/81696/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",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 does Bounded Morality address in modeling moral cognition for AI?","Question",{"text":75,"@type":76},"It addresses the gap left by approaches that encode a specific ethical theory but do not explain how moral reasoning is computed, how it scales with cognitive capacity, or why theories recur across contexts. Bounded Morality instead characterizes the computational demands imposed by moral problem structure.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the framework define the space of moral computation?",{"text":80,"@type":76},"It uses two orthogonal dimensions: moral breadth (how many entities/groups/timescales are morally relevant) and moral depth (how much inference and information integration is required to evaluate their interactions). Limited resources create unavoidable trade-offs across these dimensions.",{"name":82,"@type":73,"acceptedAnswer":83},"What does Bounded Morality imply about moral regret, moral progress, and AI alignment?",{"text":84,"@type":76},"It yields formal notions of moral regret and moral progress under constraint. For artificial systems, moral alignment depends on how moral reasoning capacity is scaled and allocated, rather than on direct imitation of human judgments.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"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":20,"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":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]