{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T21:13:00Z","timestamp":1778015580681,"version":"3.51.4"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI Ethics"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s43681-026-01022-5","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T11:13:37Z","timestamp":1772450017000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6091-6609","authenticated-orcid":false,"given":"Zichong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Lo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"issue":"7","key":"1022_CR1","doi-asserted-by":"publisher","first-page":"2973","DOI":"10.1287\/mnsc.2017.2756","volume":"64","author":"J Chan","year":"2018","unstructured":"Chan, J., Wang, J.: Hiring preferences in online labor markets: evidence of a female hiring bias. Manage. Sci. 64(7), 2973\u20132994 (2018)","journal-title":"Manage. Sci."},{"issue":"1","key":"1022_CR2","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","volume":"4","author":"L Rasmy","year":"2021","unstructured":"Rasmy, L., Xiang, Y., Xie, Z., Tao, C., Zhi, D.: Med-bert: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. NPJ Digital Med. 4(1), 86 (2021)","journal-title":"NPJ Digital Med."},{"key":"1022_CR3","unstructured":"Hoang, M., Bihorac, O.A., Rouces, J.: Aspect-based sentiment analysis using BERT. In: Proceedings of the 22nd Nordic Conference on Computational Linguistics, pp. 187\u2013196. Link\u00f6ping University Electronic Press, Turku, Finland (2019). https:\/\/aclanthology.org\/W19-6120"},{"issue":"12","key":"1022_CR4","doi-asserted-by":"publisher","first-page":"5087","DOI":"10.1109\/TSE.2021.3136169","volume":"48","author":"MH Asyrofi","year":"2022","unstructured":"Asyrofi, M.H., Yang, Z., Yusuf, I.N.B., Kang, H.J., Thung, F., Lo, D.: Biasfinder: metamorphic test generation to uncover bias for sentiment analysis systems. IEEE Trans. Softw. Eng. 48(12), 5087\u20135101 (2022). https:\/\/doi.org\/10.1109\/TSE.2021.3136169","journal-title":"IEEE Trans. Softw. Eng."},{"key":"1022_CR5","unstructured":"Angwin, J., Larson, J., Kirchner, L., Mattu, S.: Machine bias (2016). https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing"},{"key":"1022_CR6","doi-asserted-by":"crossref","unstructured":"Gill, K.S.: AI&Society: editorial volume 35.2: the trappings of AI Agency. AI & SOCIETY, Springer (2020)","DOI":"10.1007\/s00146-020-00961-9"},{"issue":"3","key":"1022_CR7","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1007\/s00146-022-01614-9","volume":"39","author":"J Rueda","year":"2024","unstructured":"Rueda, J., Rodr\u00edguez, J.D., Jounou, I.P., Hortal-Carmona, J., Aus\u00edn, T., Rodr\u00edguez-Arias, D.: \u201cjust\u2019\u2019 accuracy? procedural fairness demands explainability in ai-based medical resource allocations. AI Soc. 39(3), 1411\u20131422 (2024)","journal-title":"AI Soc."},{"issue":"2","key":"1022_CR8","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s00146-022-01458-3","volume":"38","author":"P Paraman","year":"2023","unstructured":"Paraman, P., Anamalah, S.: Ethical artificial intelligence framework for a good ai society: principles, opportunities and perils. AI Soc. 38(2), 595\u2013611 (2023)","journal-title":"AI Soc."},{"key":"1022_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, J.M., Sarro, F., Harman, M.: Maat: a novel ensemble approach to addressing fairness and performance bugs for machine learning software. In: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 1122\u20131134 (2022)","DOI":"10.1145\/3540250.3549093"},{"key":"1022_CR10","unstructured":"Kusner, M.J., Loftus, J., Russell, C., Silva, R.: Counterfactual fairness. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"issue":"1","key":"1022_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","volume":"33","author":"F Kamiran","year":"2012","unstructured":"Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1\u201333 (2012)","journal-title":"Knowl. Inf. Syst."},{"key":"1022_CR12","doi-asserted-by":"publisher","unstructured":"Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society. AIES \u201918, pp. 335\u2013340. Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3278721.3278779","DOI":"10.1145\/3278721.3278779"},{"key":"1022_CR13","doi-asserted-by":"publisher","unstructured":"Kamiran, F., Karim, A., Zhang, X.: Decision theory for discrimination-aware classification. In: 2012 IEEE 12th International Conference on Data Mining, pp. 924\u2013929 (2012). https:\/\/doi.org\/10.1109\/ICDM.2012.45","DOI":"10.1109\/ICDM.2012.45"},{"issue":"4\/5","key":"1022_CR14","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1147\/JRD.2019.2942287","volume":"63","author":"RK Bellamy","year":"2019","unstructured":"Bellamy, R.K., Dey, K., Hind, M., Hoffman, S.C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovi\u0107, A., et al.: Ai fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias. IBM J. Res. Dev. 63(4\/5), 4\u20131 (2019)","journal-title":"IBM J. Res. Dev."},{"key":"1022_CR15","doi-asserted-by":"publisher","unstructured":"Chakraborty, J., Majumder, S., Menzies, T.: Bias in machine learning software: Why? how? what to do? In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2021, pp. 429\u2013440. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3468264.3468537","DOI":"10.1145\/3468264.3468537"},{"key":"1022_CR16","doi-asserted-by":"publisher","unstructured":"Asyrofi, M.H., Yang, Z., Lo, D.: Crossasr++: A modular differential testing framework for automatic speech recognition. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2021, pp. 1575\u20131579. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3468264.3473124","DOI":"10.1145\/3468264.3473124"},{"key":"1022_CR17","doi-asserted-by":"publisher","unstructured":"Asyrofi, M.H., Yang, Z., Shi, J., Quan, C.W., Lo, D.: Can differential testing improve automatic speech recognition systems? In: 2021 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 674\u2013678 (2021). https:\/\/doi.org\/10.1109\/ICSME52107.2021.00079","DOI":"10.1109\/ICSME52107.2021.00079"},{"key":"1022_CR18","doi-asserted-by":"publisher","unstructured":"Gao, X., Saha, R.K., Prasad, M.R., Roychoudhury, A.: Fuzz testing based data augmentation to improve robustness of deep neural networks. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering. ICSE \u201920, pp. 1147\u20131158. Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3377811.3380415","DOI":"10.1145\/3377811.3380415"},{"issue":"11","key":"1022_CR19","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1145\/3361566","volume":"62","author":"K Pei","year":"2019","unstructured":"Pei, K., Cao, Y., Yang, J., Jana, S.: Deepxplore: Automated whitebox testing of deep learning systems. Commun. ACM 62(11), 137\u2013145 (2019). https:\/\/doi.org\/10.1145\/3361566","journal-title":"Commun. ACM"},{"key":"1022_CR20","doi-asserted-by":"publisher","unstructured":"Yang, Z., Shi, J., He, J., Lo, D.: Natural attack for pre-trained models of code. In: Proceedings of the 44th International Conference on Software Engineering. ICSE \u201922, pp. 1482\u20131493. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3510003.3510146","DOI":"10.1145\/3510003.3510146"},{"key":"1022_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, Z., Li, G., Ma, L., Liu, Y., Jin, Z.: Generating adversarial examples for holding robustness of source code processing models, 1169\u20131176 (2020)","DOI":"10.1609\/aaai.v34i01.5469"},{"key":"1022_CR22","doi-asserted-by":"publisher","unstructured":"Gong, C., Yang, Z., Bai, Y., Shi, J., Sinha, A., Xu, B., Lo, D., Hou, X., Fan, G.: Curiosity-driven and victim-aware adversarial policies. In: Proceedings of the 38th Annual Computer Security Applications Conference. ACSAC \u201922, pp. 186\u2013200. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3564625.3564636","DOI":"10.1145\/3564625.3564636"},{"key":"1022_CR23","unstructured":"Wu, X., Guo, W., Wei, H., Xing, X.: Adversarial policy training against deep reinforcement learning. In: 30th USENIX Security Symposium (USENIX Security 21), pp. 1883\u20131900 (2021)"},{"key":"1022_CR24","doi-asserted-by":"publisher","unstructured":"Xie, X., Ma, L., Juefei-Xu, F., Xue, M., Chen, H., Liu, Y., Zhao, J., Li, B., Yin, J., See, S.: Deephunter: A coverage-guided fuzz testing framework for deep neural networks. In: Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2019, pp. 146\u2013157. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3293882.3330579","DOI":"10.1145\/3293882.3330579"},{"key":"1022_CR25","doi-asserted-by":"publisher","unstructured":"Ma, L., Juefei-Xu, F., Zhang, F., Sun, J., Xue, M., Li, B., Chen, C., Su, T., Li, L., Liu, Y., Zhao, J., Wang, Y.: Deepgauge: Multi-granularity testing criteria for deep learning systems. In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering. ASE 2018, pp. 120\u2013131. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3238147.3238202","DOI":"10.1145\/3238147.3238202"},{"key":"1022_CR26","doi-asserted-by":"publisher","unstructured":"Ma, L., Juefei-Xu, F., Xue, M., Li, B., Li, L., Liu, Y., Zhao, J.: Deepct: Tomographic combinatorial testing for deep learning systems. In: 2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 614\u2013618 (2019). https:\/\/doi.org\/10.1109\/SANER.2019.8668044","DOI":"10.1109\/SANER.2019.8668044"},{"key":"1022_CR27","doi-asserted-by":"publisher","unstructured":"Tian, Y., Pei, K., Jana, S., Ray, B.: Deeptest: Automated testing of deep-neural-network-driven autonomous cars. In: Proceedings of the 40th International Conference on Software Engineering. ICSE \u201918, pp. 303\u2013314. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3180155.3180220","DOI":"10.1145\/3180155.3180220"},{"key":"1022_CR28","doi-asserted-by":"publisher","unstructured":"Li, Z., Ma, X., Xu, C., Cao, C.: Structural coverage criteria for neural networks could be misleading. In: 2019 IEEE\/ACM 41st International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER), pp. 89\u201392 (2019). https:\/\/doi.org\/10.1109\/ICSE-NIER.2019.00031","DOI":"10.1109\/ICSE-NIER.2019.00031"},{"key":"1022_CR29","doi-asserted-by":"publisher","unstructured":"Harel-Canada, F., Wang, L., Gulzar, M.A., Gu, Q., Kim, M.: Is neuron coverage a meaningful measure for testing deep neural networks? In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2020, pp. 851\u2013862. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3368089.3409754","DOI":"10.1145\/3368089.3409754"},{"key":"1022_CR30","doi-asserted-by":"publisher","unstructured":"Dong, Y., Zhang, P., Wang, J., Liu, S., Sun, J., Hao, J., Wang, X., Wang, L., Dong, J., Dai, T.: An empirical study on correlation between coverage and robustness for deep neural networks. In: 2020 25th International Conference on Engineering of Complex Computer Systems (ICECCS), pp. 73\u201382 (2020). https:\/\/doi.org\/10.1109\/ICECCS51672.2020.00016","DOI":"10.1109\/ICECCS51672.2020.00016"},{"key":"1022_CR31","doi-asserted-by":"publisher","unstructured":"Yan, S., Tao, G., Liu, X., Zhai, J., Ma, S., Xu, L., Zhang, X.: Correlations between deep neural network model coverage criteria and model quality. In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2020, pp. 775\u2013787. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3368089.3409671","DOI":"10.1145\/3368089.3409671"},{"key":"1022_CR32","doi-asserted-by":"publisher","unstructured":"Trujillo, M., Linares-V\u00e1squez, M., Escobar-Vel\u00e1squez, C., Dusparic, I., Cardozo, N.: Does neuron coverage matter for deep reinforcement learning? a preliminary study. In: Proceedings of the IEEE\/ACM 42nd International Conference on Software Engineering Workshops. ICSEW\u201920, pp. 215\u2013220. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3387940.3391462","DOI":"10.1145\/3387940.3391462"},{"key":"1022_CR33","doi-asserted-by":"publisher","unstructured":"Yang, Z., Shi, J., Asyrofi, M., Lo, D.: Revisiting neuron coverage metrics and quality of deep neural networks. In: 2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 408\u2013419. IEEE Computer Society, Los Alamitos (2022). https:\/\/doi.org\/10.1109\/SANER53432.2022.00056","DOI":"10.1109\/SANER53432.2022.00056"},{"key":"1022_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, M., Zhang, Y., Zhang, L., Liu, C., Khurshid, S.: Deeproad: Gan-based metamorphic testing and input validation framework for autonomous driving systems. In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering. ASE 2018, pp. 132\u2013142. Association for Computing Machinery, New York (2018). https:\/\/doi.org\/10.1145\/3238147.3238187","DOI":"10.1145\/3238147.3238187"},{"issue":"1","key":"1022_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSE.2019.2962027","volume":"48","author":"JM Zhang","year":"2022","unstructured":"Zhang, J.M., Harman, M., Ma, L., Liu, Y.: Machine learning testing: Survey, landscapes and horizons. IEEE Trans. Software Eng. 48(1), 1\u201336 (2022). https:\/\/doi.org\/10.1109\/TSE.2019.2962027","journal-title":"IEEE Trans. Software Eng."},{"key":"1022_CR36","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhang, J.M., Hort, M., Sarro, F., Harman, M.: Fairness Testing: A Comprehensive Survey and Analysis of Trends. (2022). https:\/\/doi.org\/10.48550\/ARXIV.2207.10223","DOI":"10.48550\/ARXIV.2207.10223"},{"key":"1022_CR37","doi-asserted-by":"publisher","unstructured":"Zhang, P., Wang, J., Sun, J., Dong, G., Wang, X., Wang, X., Dong, J.S., Dai, T.: White-box fairness testing through adversarial sampling. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering. ICSE \u201920, pp. 949\u2013960. Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3377811.3380331","DOI":"10.1145\/3377811.3380331"},{"key":"1022_CR38","doi-asserted-by":"publisher","unstructured":"Zheng, H., Chen, Z., Du, T., Zhang, X., Cheng, Y., Ji, S., Wang, J., Yu, Y., Chen, J.: Neuronfair: Interpretable white-box fairness testing through biased neuron identification. In: Proceedings of the 44th International Conference on Software Engineering. ICSE \u201922, pp. 1519\u20131531. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3510003.3510123","DOI":"10.1145\/3510003.3510123"},{"key":"1022_CR39","doi-asserted-by":"publisher","unstructured":"Zhang, L., Zhang, Y., Zhang, M.: Efficient white-box fairness testing through gradient search. In: Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis. ISSTA 2021, pp. 103\u2013114. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3460319.3464820","DOI":"10.1145\/3460319.3464820"},{"key":"1022_CR40","doi-asserted-by":"publisher","unstructured":"Fan, M., Wei, W., Jin, W., Yang, Z., Liu, T.: Explanation-guided fairness testing through genetic algorithm. In: Proceedings of the 44th International Conference on Software Engineering. ICSE \u201922, pp. 871\u2013882. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3510003.3510137","DOI":"10.1145\/3510003.3510137"},{"key":"1022_CR41","doi-asserted-by":"publisher","unstructured":"Yang, Z., Asyrofi, M.H., Lo, D.: Biasrv: Uncovering biased sentiment predictions at runtime. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2021, pp. 1540\u20131544. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3468264.3473117","DOI":"10.1145\/3468264.3473117"},{"key":"1022_CR42","doi-asserted-by":"publisher","unstructured":"Sun, Z., Zhang, J.M., Harman, M., Papadakis, M., Zhang, L.: Automatic testing and improvement of machine translation. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering. ICSE \u201920, pp. 974\u2013985. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3377811.3380420","DOI":"10.1145\/3377811.3380420"},{"issue":"12","key":"1022_CR43","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.1109\/TSE.2022.3141758","volume":"48","author":"E Soremekun","year":"2022","unstructured":"Soremekun, E., Udeshi, S., Chattopadhyay, S.: Astraea: Grammar-based fairness testing. IEEE Trans. Software Eng. 48(12), 5188\u20135211 (2022). https:\/\/doi.org\/10.1109\/TSE.2022.3141758","journal-title":"IEEE Trans. Software Eng."},{"key":"1022_CR44","doi-asserted-by":"crossref","unstructured":"Hort, M., Zhang, J.M., Sarro, F., Harman, M.: Fairea: A model behaviour mutation approach to benchmarking bias mitigation methods. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 994\u20131006 (2021)","DOI":"10.1145\/3468264.3468565"},{"key":"1022_CR45","doi-asserted-by":"publisher","unstructured":"Gao, X., Zhai, J., Ma, S., Shen, C., Chen, Y., Wang, Q.: Fairneuron: Improving deep neural network fairness with adversary games on selective neurons. In: Proceedings of the 44th International Conference on Software Engineering. ICSE \u201922, pp. 921\u2013933. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3510003.3510087","DOI":"10.1145\/3510003.3510087"},{"key":"1022_CR46","doi-asserted-by":"publisher","unstructured":"Zhang, M., Sun, J.: Adaptive fairness improvement based on causality analysis. In: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ESEC\/FSE 2022, pp. 6\u201317. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3540250.3549103","DOI":"10.1145\/3540250.3549103"},{"key":"1022_CR47","doi-asserted-by":"crossref","unstructured":"Chakraborty, J., Majumder, S., Menzies, T.: Bias in machine learning software: why? how? what to do? In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 429\u2013440 (2021)","DOI":"10.1145\/3468264.3468537"},{"key":"1022_CR48","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.ins.2017.09.064","volume":"425","author":"F Kamiran","year":"2018","unstructured":"Kamiran, F., Mansha, S., Karim, A., Zhang, X.: Exploiting reject option in classification for social discrimination control. Inf. Sci. 425, 18\u201333 (2018)","journal-title":"Inf. Sci."},{"issue":"2","key":"1022_CR49","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/s00146-022-01455-6","volume":"38","author":"B Giovanola","year":"2023","unstructured":"Giovanola, B., Tiribelli, S.: Beyond bias and discrimination: redefining the ai ethics principle of fairness in healthcare machine-learning algorithms. AI Soc. 38(2), 549\u2013563 (2023)","journal-title":"AI Soc."},{"issue":"2","key":"1022_CR50","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/s00146-022-01472-5","volume":"38","author":"B Catania","year":"2023","unstructured":"Catania, B., Guerrini, G., Accinelli, C.: Fairness & friends in the data science era. AI Soc. 38(2), 721\u2013731 (2023)","journal-title":"AI Soc."},{"key":"1022_CR51","first-page":"2","volume":"1","author":"S Barocas","year":"2017","unstructured":"Barocas, S., Hardt, M., Narayanan, A.: Fairness in machine learning. Nips Tutor. 1, 2 (2017)","journal-title":"Nips Tutor."},{"key":"1022_CR52","doi-asserted-by":"crossref","unstructured":"Chakraborty, J., Majumder, S., Yu, Z., Menzies, T.: Fairway: A way to build fair ml software. In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 654\u2013665 (2020)","DOI":"10.1145\/3368089.3409697"},{"key":"1022_CR53","unstructured":"Jiang, H., Nachum, O.: Identifying and correcting label bias in machine learning. CoRR: abs\/1901.04966 (2019) 1901.04966"},{"issue":"4","key":"1022_CR54","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3905\/jfds.2021.1.075","volume":"3","author":"S Das","year":"2021","unstructured":"Das, S., Donini, M., Gelman, J., Haas, K., Hardt, M., Katzman, J., Kenthapadi, K., Larroy, P., Yilmaz, P., Zafar, M.B.: Fairness measures for machine learning in finance. J. Financ. Data Sci. 3(4), 33\u201364 (2021)","journal-title":"J. Financ. Data Sci."},{"issue":"4","key":"1022_CR55","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1145\/3433949","volume":"64","author":"SA Friedler","year":"2021","unstructured":"Friedler, S.A., Scheidegger, C., Venkatasubramanian, S.: The (im) possibility of fairness: different value systems require different mechanisms for fair decision making. Commun. ACM 64(4), 136\u2013143 (2021)","journal-title":"Commun. ACM"},{"key":"1022_CR56","unstructured":"Last, F., Douzas, G., Bacao, F.: Oversampling for imbalanced learning based on k-means and smote. 2017. arXiv:1711.00837"},{"key":"1022_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, W., Weiss, J.C.: Fair decision-making under uncertainty. In: 2021 IEEE International Conference on Data Mining (ICDM), pp. 886\u2013895 (2021). IEEE","DOI":"10.1109\/ICDM51629.2021.00100"},{"key":"1022_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v049.i07","volume":"49","author":"J Fox","year":"2012","unstructured":"Fox, J., Carvalho, M.S.: The rcmdrplugin. survival package: extending the recommander interface to survival analysis. J. Stat. Softw. 49, 1\u201332 (2012)","journal-title":"J. Stat. Softw."},{"key":"1022_CR59","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.dss.2014.03.001","volume":"62","author":"S Moro","year":"2014","unstructured":"Moro, S., Cortez, P., Rita, P.: A data-driven approach to predict the success of bank telemarketing. Decis. Support Syst. 62, 22\u201331 (2014)","journal-title":"Decis. Support Syst."},{"key":"1022_CR60","unstructured":"Dheeru, D., Taniskidou, E.K.: Uci machine learning repository. http:\/\/archive.ics.uci.edu.ml (2017)"},{"issue":"2","key":"1022_CR61","doi-asserted-by":"publisher","first-page":"2473","DOI":"10.1016\/j.eswa.2007.12.020","volume":"36","author":"I-C Yeh","year":"2009","unstructured":"Yeh, I.-C., Lien, C.: The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Syst. Appl. 36(2), 2473\u20132480 (2009)","journal-title":"Expert Syst. Appl."},{"key":"1022_CR62","doi-asserted-by":"crossref","unstructured":"Angwin, J., Larson, J., Mattu, S., Kirchner, L.: Machine bias. In: Ethics of Data and Analytics, pp. 254\u2013264. Auerbach Publications (2016)","DOI":"10.1201\/9781003278290-37"},{"key":"1022_CR63","unstructured":"Laan, P.: The 2001 census in the netherlands. In: Conference The Census of Population (2000)"},{"key":"1022_CR64","doi-asserted-by":"crossref","unstructured":"Tarawneh, M., Embarak, O.: Hybrid approach for heart disease prediction using data mining techniques. In: Advances in Internet, Data and Web Technologies: The 7th International Conference on Emerging Internet, Data and Web Technologies (EIDWT-2019), pp. 447\u2013454 (2019). Springer","DOI":"10.1007\/978-3-030-12839-5_41"},{"key":"1022_CR65","unstructured":"Wightman, L.F.: LSAC National Longitudinal Bar Passage Study. Law School Admission Council, ??? (1998)"},{"key":"1022_CR66","unstructured":"Spinellis, D.: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (2021)"},{"issue":"1","key":"1022_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12864-019-6413-7","volume":"21","author":"D Chicco","year":"2020","unstructured":"Chicco, D., Jurman, G.: The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genomics 21(1), 1\u201313 (2020)","journal-title":"BMC Genomics"},{"key":"1022_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, W., Weiss, J.C.: Longitudinal fairness with censorship. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 12235\u201312243 (2022)","DOI":"10.1609\/aaai.v36i11.21484"},{"key":"1022_CR69","doi-asserted-by":"crossref","unstructured":"Biswas, S., Rajan, H.: Do the machine learning models on a crowd sourced platform exhibit bias? an empirical study on model fairness. In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 642\u2013653 (2020)","DOI":"10.1145\/3368089.3409704"},{"key":"1022_CR70","doi-asserted-by":"crossref","unstructured":"Biswas, S., Rajan, H.: Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 981\u2013993 (2021)","DOI":"10.1145\/3468264.3468536"},{"issue":"6","key":"1022_CR71","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","volume":"54","author":"N Mehrabi","year":"2021","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. 54(6), 1\u201335 (2021)","journal-title":"ACM Comput. Surv."}],"container-title":["AI and Ethics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-026-01022-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-026-01022-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-026-01022-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T20:40:00Z","timestamp":1778013600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43681-026-01022-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":71,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1022"],"URL":"https:\/\/doi.org\/10.1007\/s43681-026-01022-5","relation":{},"ISSN":["2730-5953","2730-5961"],"issn-type":[{"value":"2730-5953","type":"print"},{"value":"2730-5961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"assertion":[{"value":"3 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no Conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"CFSA is a data pre-processing framework that changes the training set by removing a subset of training instances and generating a limited amount of synthetic data to keep class balance. Because these operations can affect who benefits and who is harmed by the resulting model, this section discusses key ethical risks and the steps we take to reduce them. CFSA should be viewed as a technical tool that supports fairness improvement, not as a guarantee of fairness or a substitute for domain review and responsible deployment practices. Label-related bias and label correction: A common source of unfairness is label-related bias, where labels reflect historical or institutional decisions rather than the underlying construct that the model is intended to predict. CFSA does not perform automatic label rewriting or automatic label correction. Instead, it addresses label-related bias by identifying training instances with high counterfactual impact and prioritizing their removal, followed by a controlled synthesis step that restores class balance. This design avoids the ethical and legal risks of silently changing labels, which can hide real-world discrimination, distort accountability, or erase evidence of past harm. Counterfactual construction and limits: CFSA relies on counterfactual versions of training instances where the sensitive attribute is changed. A counterfactual edit may be unrealistic if it breaks domain constraints or causal relations (for example, changing a sensitive attribute while holding all other features fixed when some features are downstream of the sensitive attribute). For this reason, counterfactuals in CFSA are used as a diagnostic signal for ranking training instances, not as a claim about what would happen in the real world. In the revision, we will clarify the scope of this interpretation and discuss the importance of applying domain constraints during counterfactual construction to avoid invalid examples that could mislead the ranking. Synthetic data generation risks: Synthetic data can introduce harms if it amplifies stereotypes present in the original data, produces unrealistic samples, leaks sensitive patterns, or causes distribution shift that harms protected groups. CFSA uses synthesis in a restricted way: the goal is to maintain class balance after removing high-impact instances, rather than to expand the dataset without control.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical considerations"}}],"article-number":"181"}}