{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T14:34:38Z","timestamp":1759847678151,"version":"3.41.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been developed to interpret black-box models after training. This article advocates an alternative approach where the models are transparent and explainable to begin with. This approach, EVOTER, evolves rule-sets based on extended propositional logic expressions. The approach is evaluated in several prediction\/classification and prescription\/policy search domains with and without a surrogate. It is shown to discover meaningful rule-sets that perform similarly to black-box models. The rules can provide insight into the domain and make hidden biases explicit. It may also be possible to edit the rules directly to remove biases and add constraints. EVOTER thus forms a promising foundation for building trustworthy AI systems for real-world applications in the future.<\/jats:p>","DOI":"10.1145\/3702651","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T09:37:52Z","timestamp":1730799472000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["EVOTER: Evolution of Transparent Explainable Rule-sets"],"prefix":"10.1145","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5983-4531","authenticated-orcid":false,"given":"Hormoz","family":"Shahrzad","sequence":"first","affiliation":[{"name":"University of Texas at Austin, Austin, Texas, USA and Cognizant AI Labs, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4547-4731","authenticated-orcid":false,"given":"Babak","family":"Hodjat","sequence":"additional","affiliation":[{"name":"Cognizant AI Labs, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0062-0037","authenticated-orcid":false,"given":"Risto","family":"Miikkulainen","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, Texas, USA and Cognizant AI Labs, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,15]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_1_2_1","DOI":"10.1109\/ACCESS.2018.2870052"},{"doi-asserted-by":"publisher","key":"e_1_3_1_3_1","DOI":"10.1109\/TAC.1974.1100705"},{"unstructured":"Rohan Anil Andrew M. Dai Orhan Firat Melvin Johnson Dmitry Lepikhin Alexandre Passos Siamak Shakeri Emanuel Taropa Paige Bailey Zhifeng Chen et al. 2023. PaLM 2 technical report. arXiv:2305.10403 (2023).","key":"e_1_3_1_4_1"},{"key":"e_1_3_1_5_1","first-page":"303","article-title":"Multiple hypothesis testing: A review","volume":"68","author":"Austin R. S.","year":"2014","unstructured":"R. S. Austin, Isaac Dialsingh, and N. S. Altman. 2014. Multiple hypothesis testing: A review. Journal of the Indian Society of Agricultural Statistics 68 (January 2014), 303\u2013314.","journal-title":"Journal of the Indian Society of Agricultural Statistics"},{"key":"e_1_3_1_6_1","volume-title":"Simultaneous Statistical Inference","author":"Avdeeva Ligiia Igorevna","year":"1966","unstructured":"Ligiia Igorevna Avdeeva. 1966. Simultaneous Statistical Inference. Springer."},{"doi-asserted-by":"publisher","key":"e_1_3_1_7_1","DOI":"10.3389\/fdata.2021.688969"},{"doi-asserted-by":"publisher","key":"e_1_3_1_8_1","DOI":"10.1007\/s10618-023-00933-9"},{"unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI gym. arXiv:1606.01540. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1606.01540","key":"e_1_3_1_9_1"},{"unstructured":"S\u00e9bastien Bubeck Varun Chandrasekaran Ronen Eldan Johannes Gehrke Eric Horvitz Ece Kamar Peter Lee Yin Tat Lee Yuanzhi Li Scott Lundberg et al. 2023. Sparks of artificial general intelligence: Early experiments with GPT-4. arXiv:2303.12712. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2303.12712","key":"e_1_3_1_10_1"},{"doi-asserted-by":"publisher","key":"e_1_3_1_11_1","DOI":"10.1186\/s12911-020-1023-5"},{"doi-asserted-by":"publisher","key":"e_1_3_1_12_1","DOI":"10.1109\/4235.996017"},{"unstructured":"Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv:1702:08608. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1702.08608","key":"e_1_3_1_13_1"},{"unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. Retrieved from http:\/\/archive.ics.uci.edu\/ml","key":"e_1_3_1_14_1"},{"key":"e_1_3_1_15_1","first-page":"1","article-title":"Bootstrap methods: Another look at the jackknife","volume":"7","author":"Efron Bradley","year":"1992","unstructured":"Bradley Efron. 1992. Bootstrap methods: Another look at the jackknife. Springer Series in Statistics 7 (1992), 1\u201326.","journal-title":"Springer Series in Statistics"},{"doi-asserted-by":"publisher","key":"e_1_3_1_16_1","DOI":"10.1145\/3583131.3590464"},{"doi-asserted-by":"publisher","key":"e_1_3_1_17_1","DOI":"10.1145\/3583131.3590507"},{"doi-asserted-by":"publisher","key":"e_1_3_1_18_1","DOI":"10.1145\/3377930.3389842"},{"issue":"2","key":"e_1_3_1_19_1","first-page":"141","article-title":"Estimation of prediction error by using K-fold cross-validation and bootstrap for sparse logit models","volume":"81","author":"Fushiki T.","year":"2011","unstructured":"T. Fushiki. 2011. Estimation of prediction error by using K-fold cross-validation and bootstrap for sparse logit models. Journal of Statistical Computation and Simulation 81, 2 (2011), 141\u2013155.","journal-title":"Journal of Statistical Computation and Simulation"},{"doi-asserted-by":"publisher","key":"e_1_3_1_20_1","DOI":"10.1177\/105971239700500305"},{"doi-asserted-by":"publisher","key":"e_1_3_1_21_1","DOI":"10.1609\/aimag.v40i2.2850"},{"doi-asserted-by":"publisher","key":"e_1_3_1_22_1","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_3_1_23_1","first-page":"82","volume-title":"Proceedings of the 3rd Workshop on Data Mining for Medicine and Healthcare, at the 14th SIAM International Conference on Data Mining","author":"Hemberg Erik","year":"2014","unstructured":"Erik Hemberg, Kalyan Veeramachaneni, Babak Hodjat, Prashan Wanigasekara, Hormoz Shahrzad, and Una-May O\u2019Reilly. 2014. Learning decision lists with lags for physiological time series. In Proceedings of the 3rd Workshop on Data Mining for Medicine and Healthcare, at the 14th SIAM International Conference on Data Mining, 82\u201387."},{"doi-asserted-by":"publisher","key":"e_1_3_1_24_1","DOI":"10.1007\/978-1-4614-6846-2_5"},{"key":"e_1_3_1_25_1","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/978-3-319-97088-2_9","volume-title":"Genetic Programming Theory and Practice XIV","author":"Hodjat Babak","year":"2018","unstructured":"Babak Hodjat, Hormoz Shahrzad, Risto Miikkulainen, Lawrence Murray, and Chris Holmes. 2018. PRETSL: Distributed probabilistic rule evolution for time-series classification. In Genetic Programming Theory and Practice XIV. Springer, 139\u2013148."},{"doi-asserted-by":"publisher","key":"e_1_3_1_26_1","DOI":"10.1016\/j.asoc.2015.06.002"},{"unstructured":"Isaac Lage Emily Chen Jeffrey He Menaka Narayanan Been Kim Sam Gershman and Finale Doshi-Velez. 2019. An evaluation of the human-interpretability of explanation. arXiv:1902.00006. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1902.00006","key":"e_1_3_1_27_1"},{"doi-asserted-by":"publisher","key":"e_1_3_1_28_1","DOI":"10.1145\/3306618.3314229"},{"doi-asserted-by":"publisher","key":"e_1_3_1_29_1","DOI":"10.3390\/e23010018"},{"doi-asserted-by":"publisher","key":"e_1_3_1_30_1","DOI":"10.5555\/3295222.3295230"},{"key":"e_1_3_1_31_1","volume-title":"Handbook of Evolutionary Machine Learning","author":"Miikkulainen Risto","year":"2023","unstructured":"Risto Miikkulainen. 2023. Evolutionary supervised machine learning. In Handbook of Evolutionary Machine Learning. W. Banzhaf, P. Machado, and M. Zhang (Eds.), Springer, New York."},{"doi-asserted-by":"publisher","key":"e_1_3_1_32_1","DOI":"10.1109\/TEVC.2021.3063217"},{"key":"e_1_3_1_33_1","volume-title":"Proceedings of the IEEE Symposium Series in Computational Intelligence","author":"Miikkulainen Risto","year":"2017","unstructured":"Risto Miikkulainen, Hormoz Shahrzad, Nigel Duffy, and Phil Long. 2017. How to select a winner in evolutionary optimization? In Proceedings of the IEEE Symposium Series in Computational Intelligence. IEEE. Retrieved from http:\/\/www.cs.utexas.edu\/users\/ai-lab?miikkulainen:ssci17"},{"doi-asserted-by":"publisher","key":"e_1_3_1_34_1","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_1_35_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3583558","article-title":"From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI","volume":"55","author":"Nauta Meike","year":"2022","unstructured":"Meike Nauta, Jan Trienes, Shreyasi Pathak, Elisa Nguyen, Michelle Peters, Yasmin Schmitt, J\u00f6rg Schl\u00f6tterer, Maurice van Keulen, and Christin Seifert. 2022. From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI. Computing Surveys 55 (2022), 1\u201342. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:246063780","journal-title":"Computing Surveys"},{"key":"e_1_3_1_36_1","first-page":"83","volume-title":"Genetic Programming","author":"O\u2019Neill Michael","year":"1998","unstructured":"Michael O\u2019Neill and Conor Ryan. 1998. Grammatical evolution: Evolving programs for an arbitrary language. In Genetic Programming. W. Banzhaf, P. Poli, M. Schoenauer, and T. C. Fogarty (Eds.), Springer, 83\u201396."},{"unstructured":"Jaume Bacardit Pe\u00f1arroya. 2004. Pittsburgh genetic-based machine learning in the data mining era: Representations generalization and run-time. Retrieved from https:\/\/ico2s.org\/data\/papers\/Bacardit2004.pdf","key":"e_1_3_1_37_1"},{"doi-asserted-by":"publisher","key":"e_1_3_1_38_1","DOI":"10.3897\/jucs.76608"},{"key":"e_1_3_1_39_1","first-page":"1135","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916)","author":"Ribeiro Marco Tulio","year":"2016","unstructured":"Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. \u201cWhy should i trust you?\u201d: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916). ACM, New York, NY, 1135\u20131144."},{"doi-asserted-by":"publisher","key":"e_1_3_1_40_1","DOI":"10.1126\/science.1165893"},{"doi-asserted-by":"publisher","key":"e_1_3_1_41_1","DOI":"10.1007\/s10618-022-00867-8"},{"doi-asserted-by":"publisher","key":"e_1_3_1_42_1","DOI":"10.1214\/aos\/1176344136"},{"doi-asserted-by":"publisher","key":"e_1_3_1_43_1","DOI":"10.1162\/isal_a_00113"},{"key":"e_1_3_1_44_1","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/978-3-030-39958-0_14","volume-title":"Genetic Programming Theory and Practice XVII","author":"Shahrzad Hormoz","year":"2020","unstructured":"Hormoz Shahrzad, Babak Hodjat, Camille Dolle, Andrej Denissov, Simon Lau, Donn Goodhew, Justin Dyer, and Risto Miikkulainen. 2020. Enhanced optimization with composite objectives and novelty pulsation. In Genetic Programming Theory and Practice XVII. Wolfgang Banzhaf, Erik Goodman, Leigh Sheneman, Leonardo Trujillo, and Bill Worzel (Eds.), Springer, New York, 275\u2013293."},{"doi-asserted-by":"publisher","key":"e_1_3_1_45_1","DOI":"10.1145\/2908812.2908911"},{"doi-asserted-by":"publisher","key":"e_1_3_1_46_1","DOI":"10.1007\/s10462-011-9212-3"},{"key":"e_1_3_1_47_1","first-page":"781670","article-title":"Impact of HbA1c measurement on hospital readmission rates: Analysis of 70,000 clinical database patient records","volume":"2014","author":"Strack Beata","year":"2014","unstructured":"Beata Strack, Jonathan Deshazo, Chris Gennings, Juan Luis Olmo Ortiz, Sebastian Ventura, Krzysztof Cios, and John Clore. 2014. Impact of HbA1c measurement on hospital readmission rates: Analysis of 70,000 clinical database patient records. BioMed Research International 2014 (2014), 781670.","journal-title":"BioMed Research International"},{"unstructured":"Norman Tasfi. 2016. PyGame Learning Environment. Retrieved from https:\/\/github.com\/ntasfi\/PyGame-Learning-Environment.","key":"e_1_3_1_48_1"},{"doi-asserted-by":"publisher","key":"e_1_3_1_49_1","DOI":"10.1109\/TNNLS.2020.3027314"},{"unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et al. 2023. LLaMA: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2302.13971","key":"e_1_3_1_50_1"},{"doi-asserted-by":"publisher","key":"e_1_3_1_51_1","DOI":"10.1109\/TNNLS.2019.2944672"}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702651","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3702651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:03Z","timestamp":1750295883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702651"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3702651"],"URL":"https:\/\/doi.org\/10.1145\/3702651","relation":{},"ISSN":["2688-3007"],"issn-type":[{"type":"electronic","value":"2688-3007"}],"subject":[],"published":{"date-parts":[[2025,5,15]]},"assertion":[{"value":"2022-11-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}