{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T08:23:48Z","timestamp":1785313428988,"version":"3.55.0"},"reference-count":111,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:00:00Z","timestamp":1692921600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2024,1,31]]},"abstract":"<jats:p>An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do concerning artificial intelligence, especially the super-intelligent one. As such, these results serve as guidelines, reminders, and warnings to AI safety, AI policy, and governance researchers. These might enable solutions to some long-standing questions in the form of formalizing theories in the framework of constraint satisfaction without committing to one option. We strongly believe this to be the most prudent approach to long-term AI safety initiatives. In this article, we have categorized impossibility theorems applicable to AI into five mechanism-based categories: Deduction, indistinguishability, induction, tradeoffs, and intractability. We found that certain theorems are too specific or have implicit assumptions that limit application. Also, we added new results (theorems) such as the unfairness of explainability, the first explainability-related result in the induction category. The remaining results deal with misalignment between the clones and put a limit to the self-awareness of agents. We concluded that deductive impossibilities deny 100%-guarantees for security. In the end, we give some ideas that hold potential in explainability, controllability, value alignment, ethics, and group decision-making.<\/jats:p>","DOI":"10.1145\/3603371","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T11:07:55Z","timestamp":1685704075000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Impossibility Results in AI: A Survey"],"prefix":"10.1145","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7564-6805","authenticated-orcid":false,"given":"Mario","family":"Brcic","sequence":"first","affiliation":[{"name":"University of Zagreb Faculty of Electrical Engineering and Computing, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9637-1161","authenticated-orcid":false,"given":"Roman V.","family":"Yampolskiy","sequence":"additional","affiliation":[{"name":"University of Louisville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,8,25]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"261","article-title":"Why philosophers should care about computational complexity","author":"Aaronson Scott","year":"2013","unstructured":"Scott Aaronson. 2013. Why philosophers should care about computational complexity. Computab.: Turing, G\u00f6del, Church Bey. (2013), 261\u2013328.","journal-title":"Computab.: Turing, G\u00f6del, Church Bey."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32784-1_1"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12202"},{"key":"e_1_3_1_5_2","first-page":"7786","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS\u201918)","author":"Alvarez-Melis David","year":"2018","unstructured":"David Alvarez-Melis and Tommi S. Jaakkola. 2018. Towards robust interpretability with self-explaining neural networks. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS\u201918). Curran Associates Inc., Red Hook, NY, 7786\u20137795."},{"key":"e_1_3_1_6_2","article-title":"Occam\u2019s razor is insufficient to infer the preferences of irrational agents","volume":"31","author":"Armstrong Stuart","year":"2018","unstructured":"Stuart Armstrong and S\u00f6ren Mindermann. 2018. Occam\u2019s razor is insufficient to infer the preferences of irrational agents. Adv. Neural Inf. Process. Syst. 31 (2018). Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/d89a66c7c80a29b1bdbab0f2a1a94af8-Abstract.html.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_1_7_2","series-title":"(Advanced Series on Mathematical Psychology","first-page":"1","volume-title":"Descriptive and Normative Approaches to Human Behavior","author":"Arrhenius Gustaf","year":"2011","unstructured":"Gustaf Arrhenius. 2011. The impossibility of a satisfactory population ethics. In Descriptive and Normative Approaches to Human Behavior. (Advanced Series on Mathematical Psychology, Vol. 3). World Scientific, 1\u201326. DOI:10.1142\/9789814368018_0001"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1086\/256963"},{"key":"e_1_3_1_9_2","volume-title":"Introduction to Cybernetics.1961 Edition","author":"Ashby Ross W.","year":"1961","unstructured":"Ross W. Ashby. 1961. Introduction to Cybernetics.1961 Edition. Chapman & Hall."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-008-9244-5"},{"issue":"1","key":"e_1_3_1_11_2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s11229-004-6221-7","article-title":"The surveyability of mathematical proof: A historical perspective","volume":"148","author":"Bassler O. Bradley","year":"2006","unstructured":"O. Bradley Bassler. 2006. The surveyability of mathematical proof: A historical perspective. Synthese 148, 1 (2006), 99\u2013133. Retrieved from https:\/\/www.jstor.org\/stable\/20118682.","journal-title":"Synthese"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0002-3"},{"key":"e_1_3_1_13_2","unstructured":"Iavor I. Bojinov and Guillaume Basse. 2020. A General Theory of Identification. Retrieved from https:\/\/www.hbs.edu\/faculty\/Pages\/item.aspx?num=57688."},{"issue":"2","key":"e_1_3_1_14_2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11225-006-9011-z","article-title":"An impossibility theorem on beliefs in games","volume":"84","author":"Brandenburger Adam","year":"2006","unstructured":"Adam Brandenburger and H. Jerome Keisler. 2006. An impossibility theorem on beliefs in games. Studia Logica: Int. J. Symbol. Logic 84, 2 (2006), 211\u2013240. Retrieved from https:\/\/www.jstor.org\/stable\/20016831.","journal-title":"Studia Logica: Int. J. Symbol. Logic"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2014.895108"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.083"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aam.2004.10.003"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/0149-7189(79)90048-X"},{"key":"e_1_3_1_19_2","article-title":"Incorrigibility in the CIRL framework","author":"Carey Ryan","year":"2018","unstructured":"Ryan Carey. 2018. Incorrigibility in the CIRL framework. arXiv:1709.06275 [cs] (June 2018).","journal-title":"arXiv:1709.06275 [cs]"},{"key":"e_1_3_1_20_2","unstructured":"Rudolf Carnap and Yehoshua Bar-Hillel. 1952. An outline of a theory of semantic information. Retrieved from https:\/\/dspace.mit.edu\/handle\/1721.1\/4821. Research Laboratory of Electronics Massachusetts Institute of Technology."},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","DOI":"10.1142\/0531","volume-title":"Information, Randomness and Incompleteness: Papers on Algorithmic Information Theory","author":"Chaitin Gregory J.","year":"1987","unstructured":"Gregory J. Chaitin. 1987. Information, Randomness and Incompleteness: Papers on Algorithmic Information Theory. World Scientific Publishing Company, Singapore."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/1149114.1149119"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.2307\/2371045"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1080\/00207727008920220"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2014.0540"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3968077"},{"key":"e_1_3_1_27_2","volume-title":"The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World (1st ed.)","author":"Domingos Pedro","year":"2015","unstructured":"Pedro Domingos. 2015. The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World (1st ed.). Basic Books, New York."},{"key":"e_1_3_1_28_2","first-page":"0210","volume-title":"Proceedings of the 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","author":"Dosilovic Filip Karlo","year":"2018","unstructured":"Filip Karlo Dosilovic, Mario Brcic, and Nikica Hlupic. 2018. Explainable artificial intelligence: A survey. In Proceedings of the 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO). MIPRO Association, 0210\u20130215. DOI:10.23919\/MIPRO.2018.8400040"},{"key":"e_1_3_1_29_2","article-title":"Impossibility and uncertainty theorems in AI value alignment (or why your AGI should not have a utility function)","author":"Eckersley Peter","year":"2019","unstructured":"Peter Eckersley. 2019. Impossibility and uncertainty theorems in AI value alignment (or why your AGI should not have a utility function). arXiv:1901.00064 [cs] (Mar. 2019).","journal-title":"arXiv:1901.00064 [cs]"},{"key":"e_1_3_1_30_2","first-page":"2926","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ecoffet Adrien","year":"2021","unstructured":"Adrien Ecoffet and Joel Lehman. 2021. Reinforcement learning under moral uncertainty. In Proceedings of the International Conference on Machine Learning. PMLR, 2926\u20132936. Retrieved from http:\/\/proceedings.mlr.press\/v139\/ecoffet21a.html."},{"key":"e_1_3_1_31_2","article-title":"Truthful AI: Developing and governing AI that does not lie","author":"Evans Owain","year":"2021","unstructured":"Owain Evans, Owen Cotton-Barratt, Lukas Finnveden, Adam Bales, Avital Balwit, Peter Wills, Luca Righetti, and William Saunders. 2021. Truthful AI: Developing and governing AI that does not lie. arXiv:2110.06674 [cs] (Oct. 2021).","journal-title":"arXiv:2110.06674 [cs]"},{"key":"e_1_3_1_32_2","article-title":"Reinforcement learning with a corrupted reward channel","author":"Everitt Tom","year":"2017","unstructured":"Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, and Shane Legg. 2017. Reinforcement learning with a corrupted reward channel. arXiv:1705.08417 [cs, stat] (Aug. 2017).","journal-title":"arXiv:1705.08417 [cs, stat]"},{"key":"e_1_3_1_33_2","article-title":"AGI safety literature review","author":"Everitt Tom","year":"2018","unstructured":"Tom Everitt, Gary Lea, and Marcus Hutter. 2018. AGI safety literature review. arXiv:1805.01109 [cs] (May 2018).","journal-title":"arXiv:1805.01109 [cs]"},{"key":"e_1_3_1_34_2","volume-title":"Philosophy and Computing: An Introduction (1st edition ed.)","author":"Floridi Luciano","year":"1999","unstructured":"Luciano Floridi. 1999. Philosophy and Computing: An Introduction (1st edition ed.). Routledge, London; New York."},{"key":"e_1_3_1_35_2","volume-title":"On the Impossibility of Predicting the Behavior of Rational Agents","author":"Foster Dean","year":"2001","unstructured":"Dean Foster and H. Peyton Young. 2001. On the Impossibility of Predicting the Behavior of Rational Agents. Technical Report 423. The Johns Hopkins University, Department of Economics. Retrieved from https:\/\/ideas.repec.org\/p\/jhu\/papers\/423.html."},{"issue":"1","key":"e_1_3_1_36_2","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1613\/jair.3126","article-title":"Automated search for impossibility theorems in social choice theory: Ranking sets of objects","volume":"40","author":"Geist Christian","year":"2011","unstructured":"Christian Geist and Ulle Endriss. 2011. Automated search for impossibility theorems in social choice theory: Ranking sets of objects. J. Artif. Intell. Res. 40, 1 (Jan. 2011), 143\u2013174.","journal-title":"J. Artif. Intell. Res."},{"key":"e_1_3_1_37_2","unstructured":"C. Giraud-Carrier. 2005. Toward a justification of meta-learning: Is the no free lunch theorem a showstopper? Retrieved from https:\/\/www.semanticscholar.org\/paper\/Toward-a-Justification-of-Meta-learning-3A-Is-the-No-Giraud-Carrier\/fee1abe79f179f465d2725be63e97a50034bc511."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-349-17295-5_4"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.2307\/2020332"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3453474"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01700692"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/32"},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198754626.001.0001","volume-title":"The Age of Em: Work, Love, and Life when Robots Rule the Earth","author":"Hanson Robin","year":"2016","unstructured":"Robin Hanson. 2016. The Age of Em: Work, Love, and Life when Robots Rule the Earth. Oxford University Press, Oxford, New York."},{"key":"e_1_3_1_44_2","first-page":"146","volume-title":"Proceedings of the International Symposium of Engineering of Intelligent Systems (EIS\u201998)","author":"Hernandez-Orallo Jose","year":"1998","unstructured":"Jose Hernandez-Orallo. 1998. A formal definition of intelligence based on an intensional variant of Kolmogorov complexity. In Proceedings of the International Symposium of Engineering of Intelligent Systems (EIS\u201998). ICSC Press, 146\u2013163."},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.2307\/2214318"},{"key":"e_1_3_1_46_2","unstructured":"Proceedings of the Workshop on Artificial Intelligence Safety 2021 co-located with the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI'21)"},{"key":"e_1_3_1_47_2","unstructured":"Hsueh-Ling Huynh and Balazs Szentes. 1999. Believing the Unbelievable: The Dilemma of Self-Belief. Retrieved from https:\/\/personal.lse.ac.uk\/szentes\/docs\/bub3.pdf."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00140-3"},{"key":"e_1_3_1_49_2","article-title":"AI safety via debate","author":"Irving Geoffrey","year":"2018","unstructured":"Geoffrey Irving, Paul Christiano, and Dario Amodei. 2018. AI safety via debate. arXiv:1805.00899 [cs, stat] (Oct. 2018).","journal-title":"arXiv:1805.00899 [cs, stat]"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.3390\/philosophies7060134"},{"key":"e_1_3_1_51_2","first-page":"1254","volume-title":"Proceedings of the 43rd International Convention on Information, Communication and Electronic Technology (MIPRO)","author":"Juric Mislav","year":"2020","unstructured":"Mislav Juric, Agneza Sandic, and Mario Brcic. 2020. AI safety: State of the field through quantitative lens. In Proceedings of the 43rd International Convention on Information, Communication and Electronic Technology (MIPRO). MIPRO Association, 1254\u20131259. DOI:10.23919\/MIPRO48935.2020.9245153"},{"key":"e_1_3_1_52_2","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/978-1-4684-2001-2_9","volume-title":"Complexity of Computer Computations","author":"Karp Richard M.","year":"1972","unstructured":"Richard M. Karp. 1972. Reducibility among combinatorial problems. In Complexity of Computer Computations. Springer, 85\u2013103."},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1972.1100128"},{"issue":"2","key":"e_1_3_1_54_2","first-page":"335","article-title":"Controllability of dynamical systems. A survey","volume":"61","author":"Klamka Jerzy","year":"2013","unstructured":"Jerzy Klamka. 2013. Controllability of dynamical systems. A survey. Bull. Polish Acad. Sci.-Technic. Sci. 61, 2 (2013), 335\u2013342. Retrieved from http:\/\/journals.pan.pl\/dlibra\/publication\/edition\/83697DOI-10.2478\/bpasts-2013-0031.","journal-title":"Bull. Polish Acad. Sci.-Technic. Sci."},{"key":"e_1_3_1_55_2","first-page":"463","volume-title":"Proceedings of the 15th International Conference on Neural Information Processing Systems (NIPS\u201902)","author":"Kleinberg Jon","year":"2002","unstructured":"Jon Kleinberg. 2002. An impossibility theorem for clustering. In Proceedings of the 15th International Conference on Neural Information Processing Systems (NIPS\u201902). MIT Press, Cambridge, MA, 463\u2013470."},{"key":"e_1_3_1_56_2","article-title":"Inherent trade-offs in the Fair Determination of Risk Scores","author":"Kleinberg Jon","year":"2016","unstructured":"Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan. 2016. Inherent trade-offs in the Fair Determination of Risk Scores. arXiv:1609.05807 [cs, stat] (Nov. 2016).","journal-title":"arXiv:1609.05807 [cs, stat]"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1111\/1467-999X.00147"},{"key":"e_1_3_1_58_2","first-page":"223","volume-title":"Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence: Papers from the Ray Solomonoff 85th Memorial Conference, Melbourne, VIC, Australia, November 30\u2013December 2, 2011","author":"Lattimore Tor","year":"2013","unstructured":"Tor Lattimore and Marcus Hutter. 2013. No free lunch versus Occam\u2019s razor in supervised learning. In Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence: Papers from the Ray Solomonoff 85th Memorial Conference, Melbourne, VIC, Australia, November 30\u2013December 2, 2011, David L. Dowe (Ed.). Springer, Berlin, 223\u2013235. DOI:10.1007\/978-3-642-44958-1_17"},{"issue":"54","key":"e_1_3_1_59_2","first-page":"479","article-title":"How gruesome are the no-free-lunch theorems for machine learning?","author":"Lauc Davor","year":"2018","unstructured":"Davor Lauc. 2018. How gruesome are the no-free-lunch theorems for machine learning? Croat. J. Philos. XVIII, 54 (2018), 479\u2013485. Retrieved from https:\/\/www.ceeol.com\/search\/article-detail?id=734617.","journal-title":"Croat. J. Philos."},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0080769"},{"key":"e_1_3_1_61_2","unstructured":"Yujia Li David Choi and Junyoung Chung. 2022. Competitive programming with AlphaCode. Retrieved from https:\/\/storage.googleapis.com\/deepmind-media\/AlphaCode\/competition_level_code_generation_with_alphacode.pdf."},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-017-1836-5"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1038\/35023282"},{"key":"e_1_3_1_64_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Locatello Francesco","year":"2019","unstructured":"Francesco Locatello, Stefan Bauer, Mario Lu\u010di\u0107, Gunnar R\u00e4tsch, Sylvain Gelly, Bernhard Sch\u00f6lkopf, and Olivier Frederic Bachem. 2019. Challenging common assumptions in the unsupervised learning of disentangled representations. In Proceedings of the International Conference on Machine Learning. Retrieved from http:\/\/proceedings.mlr.press\/v97\/locatello19a.html."},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.2307\/2266895"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.5840\/monist197962319"},{"issue":"1","key":"e_1_3_1_67_2","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1080\/00455091.2005.10716582","article-title":"The many moral particularisms","volume":"35","author":"McKeever Sean","year":"2005","unstructured":"Sean McKeever and Michael Ridge. 2005. The many moral particularisms. Canad. J. Philos. 35, 1 (2005), 83\u2013106. Retrieved from https:\/\/www.jstor.org\/stable\/40232238.","journal-title":"Canad. J. Philos."},{"key":"e_1_3_1_68_2","first-page":"129","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917)","author":"Mhamdi El Mahdi El","year":"2017","unstructured":"El Mahdi El Mhamdi, Rachid Guerraoui, Hadrien Hendrikx, and Alexandre Maurer. 2017. Dynamic safe interruptibility for decentralized multi-agent reinforcement learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917). Curran Associates Inc., Red Hook, NY, 129\u2013139."},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.84.3.231"},{"key":"e_1_3_1_70_2","unstructured":"Caspar Oesterheld. 2017. Multiverse-wide Cooperation via Correlated Decision Making. Retrieved from https:\/\/longtermrisk.org\/multiverse-wide-cooperation-via-correlated-decision-making\/."},{"key":"e_1_3_1_71_2","first-page":"557","volume-title":"Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence (UAI\u201916)","author":"Orseau Laurent","year":"2016","unstructured":"Laurent Orseau and Stuart Armstrong. 2016. Safely interruptible agents. In Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence (UAI\u201916). AUAI Press, Arlington, Virginia, 557\u2013566."},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1093\/019824908X.001.0001"},{"key":"e_1_3_1_73_2","doi-asserted-by":"crossref","DOI":"10.1002\/9781119620785","volume-title":"Key Performance Indicators: Developing, Implementing, and Using Winning KPIs (4th edition ed.)","author":"Parmenter David","year":"2019","unstructured":"David Parmenter. 2019. Key Performance Indicators: Developing, Implementing, and Using Winning KPIs (4th edition ed.). Wiley, Hoboken, NJ."},{"key":"e_1_3_1_74_2","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters Jonas","year":"2017","unstructured":"Jonas Peters, Dominik Janzing, and Bernhard Sch\u00f6lkopf. 2017. Elements of Causal Inference: Foundations and Learning Algorithms. MIT Press, Cambridge, MA."},{"key":"e_1_3_1_75_2","article-title":"Formal mathematics statement curriculum learning","author":"Polu Stanislas","year":"2022","unstructured":"Stanislas Polu, Jesse Michael Han, Kunhao Zheng, Mantas Baksys, Igor Babuschkin, and Ilya Sutskever. 2022. Formal mathematics statement curriculum learning. arXiv:2202.01344 [cs] (Feb. 2022).","journal-title":"arXiv:2202.01344 [cs]"},{"key":"e_1_3_1_76_2","volume-title":"Proceedings of the 6th International Conference of Computer Ethics: Philosophical Enquiry","author":"Reynolds Carson J.","year":"2005","unstructured":"Carson J. Reynolds. 2005. On the computational complexity of action evaluations. In Proceedings of the 6th International Conference of Computer Ethics: Philosophical Enquiry. Retrieved from https:\/\/www.media.mit.edu\/publications\/on-the-computational-complexity-of-action-evaluations\/."},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-019-00012-4"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.2307\/1990888"},{"key":"e_1_3_1_79_2","article-title":"The impossibility theorem of machine fairness\u2014A causal perspective","author":"Saravanakumar Kailash Karthik","year":"2021","unstructured":"Kailash Karthik Saravanakumar. 2021. The impossibility theorem of machine fairness\u2014A causal perspective. arXiv:2007.06024 [cs, stat] (Jan. 2021).","journal-title":"arXiv:2007.06024 [cs, stat]"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1086\/592550"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1086\/693929"},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDS52072.2021.00107"},{"key":"e_1_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.128.070501"},{"key":"e_1_3_1_84_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-15524-1","volume-title":"Why Greatness Cannot Be Planned: The Myth of the Objective","author":"Stanley Kenneth O.","year":"2015","unstructured":"Kenneth O. Stanley and Joel Lehman. 2015. Why Greatness Cannot Be Planned: The Myth of the Objective. Springer, Cham, Switzerland."},{"key":"e_1_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1234-981X(199707)5:3<305::AID-EURO184>3.0.CO;2-4"},{"key":"e_1_3_1_86_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2009.02.005"},{"key":"e_1_3_1_87_2","first-page":"152","volume-title":"Logic, Semantics, Metamathematics","author":"Tarski Alfred","year":"1936","unstructured":"Alfred Tarski. 1936. The concept of truth in formalized languages. In Logic, Semantics, Metamathematics, Alfred Tarski (Ed.). Oxford University Press, 152\u2013278."},{"key":"e_1_3_1_88_2","volume-title":"Proceedings of the AAAI Workshop: AI, Ethics, and Society","author":"Taylor Jessica","year":"2016","unstructured":"Jessica Taylor. 2016. Quantilizers: A safer alternative to maximizers for limited optimization. In Proceedings of the AAAI Workshop: AI, Ethics, and Society."},{"key":"e_1_3_1_89_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2003.09.007"},{"key":"e_1_3_1_90_2","volume-title":"Virtue\u2019s Reasons","author":"Tsu Peter Shiu-Hwa","year":"2017","unstructured":"Peter Shiu-Hwa Tsu. 2017. Can virtue be codified?: An inquiry on the basis of four conceptions of virtue. In Virtue\u2019s Reasons. Routledge."},{"key":"e_1_3_1_91_2","doi-asserted-by":"publisher","DOI":"10.1112\/plms\/s2-42.1.230"},{"key":"e_1_3_1_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"e_1_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-017-9440-6"},{"key":"e_1_3_1_94_2","volume-title":"Impossibility Results for the Online Verification of Ethical and Legal Behaviour of Robots","author":"Leeuwen Jan van","year":"2021","unstructured":"Jan van Leeuwen and Jiri Wiedermann. 2021. Impossibility Results for the Online Verification of Ethical and Legal Behaviour of Robots. Technical Report UU-PCS-2021-02. Utrecht University, Utrecht. Retrieved from http:\/\/www.cs.uu.nl\/groups\/AD\/UU-PCS-2021-02.pdf."},{"key":"e_1_3_1_95_2","unstructured":"Vernor Vinge. 1993. Technological singularity. Retrieved from https:\/\/frc.ri.cmu.edu\/hpm\/book98\/com.ch1\/vinge.singularity.html."},{"key":"e_1_3_1_96_2","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.2.040327"},{"key":"e_1_3_1_97_2","volume-title":"Center for Research on Concepts and Cognition","unstructured":"Pei Wang. 1995. On the working definition of intelligence. Technical Report 94, Center for Research on Concepts and Cognition, Indiana University, Bloomington, IN. Retrieved from https:\/\/www.researchgate.net\/publication\/2339604_On_the_Working_Definition_of_Intelligence."},{"key":"e_1_3_1_98_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.7.1391"},{"key":"e_1_3_1_99_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.65.016128"},{"key":"e_1_3_1_100_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2008.03.040"},{"key":"e_1_3_1_101_2","article-title":"Constraints on physical reality arising from a formalization of knowledge","author":"Wolpert David H.","year":"2018","unstructured":"David H. Wolpert. 2018. Constraints on physical reality arising from a formalization of knowledge. arXiv:1711.03499 [physics] (June 2018).","journal-title":"arXiv:1711.03499 [physics]"},{"key":"e_1_3_1_102_2","article-title":"What is important about the no free lunch theorems?","author":"Wolpert David H.","year":"2020","unstructured":"David H. Wolpert. 2020. What is important about the no free lunch theorems? arXiv:2007.10928 [cs, stat] (July 2020).","journal-title":"arXiv:2007.10928 [cs, stat]"},{"key":"e_1_3_1_103_2","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585893"},{"key":"e_1_3_1_104_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2005.856205"},{"key":"e_1_3_1_105_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63703-7_16"},{"key":"e_1_3_1_106_2","doi-asserted-by":"publisher","DOI":"10.1088\/1402-4896\/aa7ca8"},{"key":"e_1_3_1_107_2","article-title":"Personal universes: A solution to the multi-agent value alignment problem","author":"Yampolskiy Roman V.","year":"2019","unstructured":"Roman V. Yampolskiy. 2019. Personal universes: A solution to the multi-agent value alignment problem. arXiv:1901.01851 [cs] (Jan. 2019).","journal-title":"arXiv:1901.01851 [cs]"},{"key":"e_1_3_1_108_2","doi-asserted-by":"publisher","DOI":"10.1142\/S2705078520500150"},{"key":"e_1_3_1_109_2","doi-asserted-by":"publisher","DOI":"10.1142\/S2705078520500034"},{"key":"e_1_3_1_110_2","doi-asserted-by":"publisher","DOI":"10.13052\/jcsm2245-1439.1132"},{"key":"e_1_3_1_111_2","doi-asserted-by":"publisher","DOI":"10.2178\/bsl\/1058448677"},{"key":"e_1_3_1_112_2","article-title":"Consequences of misaligned AI","author":"Zhuang Simon","year":"2021","unstructured":"Simon Zhuang and Dylan Hadfield-Menell. 2021. Consequences of misaligned AI. arXiv:2102.03896 [cs] (Feb. 2021).","journal-title":"arXiv:2102.03896 [cs]"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603371","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:25Z","timestamp":1750178785000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603371"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,25]]},"references-count":111,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,31]]}},"alternative-id":["10.1145\/3603371"],"URL":"https:\/\/doi.org\/10.1145\/3603371","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,25]]},"assertion":[{"value":"2022-02-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-31","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}