A Theory of Justified Abstention for Uncertain Materials AI Models

iamrp.net-Z327-1791515266-m232437424 1791515266 Institute for Advanced Materials Research Press info@iamrp.net Institute for Advanced Materials Research Press Journal of Artificial Intelligence for Materials Science J. Artif. Intell. Mater. Sci. 3149-8957 2025 4 1 A Theory of Justified Abstention for Uncertain Materials AI Models Omar Khalid Sara Nadeem Bilal Farooq Hina Saeed 2025 10.68159/m232437424 https://iamrp.net/pub/journal/1/article/m232437424 Omee SS, Fu N, Dong R, Hu M, Hu J. Structure-based out-of-distribution (OOD) materials property prediction: A benchmark study. npj Comput Mater. 2024;10(1):144. Schuster D. Abstaining machine learning: Philosophical considerations. AI SOC. 2025;40(6):4213-33. Geifman Y, El-Yaniv R. Selective classification for deep neural networks. Adv Neural Inf Process Syst. 2017;30:4878-87. Thulasidasan S, Bhattacharya T, Bilmes J, Chennupati G, Mohd-Yusof J. Combating label noise in deep learning using abstention. arXiv preprint arXiv:1905.10964. 2019 May 27. Geifman Y, El-Yaniv R. SelectiveNet: A deep neural network with an integrated reject option. In: International Conference on Machine Learning. New York, NY: PMLR; 2019:2151-9. Lamy A, Zhong Z, Menon AK, Verma N. Noise-tolerant fair classification. Adv Neural Inf Process Syst. 2019;32:284-94. Franc V, Prusa D, Voracek V. Optimal strategies for reject option classifiers. J Mach Learn Res. 2023;24(11):1-49. Pugnana A, Perini L, Davis J, Ruggieri S. Deep neural network benchmarks for selective classification. arXiv preprint arXiv:2401.12708. 2024 Jan 23. Gelbhart R, El-Yaniv R. The relationship between agnostic selective classification, active learning and the disagreement coefficient. J Mach Learn Res. 2019;20(33):1-38. Varshney N, Mishra S, Baral C. Investigating selective prediction approaches across several tasks in IID, OOD, and adversarial settings. In: Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg, PA: Association for Computational Linguistics; 2022:1995-2002. Narasimhan H, Menon AK, Jitkrittum W, Kumar S. Plugin estimators for selective classification with out-of-distribution detection. arXiv preprint arXiv:2301.12386. 2023 Jan 29. Ly C, Nizinski C, McDonald IV LW, Chalifoux A, Hagen A. Out-of-distribution detection with non-parametric density estimation for models predicting processing history of uranium ore concentrates. Comput Mater Sci. 2025;259:114148. Theunissen L, Mortier T, Saeys Y, Waegeman W. Evaluation of out-of-distribution detection methods for data shifts in single-cell transcriptomics. Brief Bioinform. 2025;26(3):bbaf239. Cui P, Wang J. Out-of-distribution (OOD) detection based on deep learning: A review. Electronics. 2022;11(21):3500. Jungo A, Doorenbos L, Da Col T, Beelen M, Zinkernagel M, Márquez-Neila P, et al. Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery. Int J Comput Assist Radiol Surg. 2023;18(6):1085-91. Lv X, Li M, Chen J, Dong Z, Han S, Liao B. Out-of-distribution detection via LLM-guided outlier generation for text-attributed graph. In: Findings of the Association for Computational Linguistics: ACL 2025. Stroudsburg, PA: Association for Computational Linguistics; 2025:19544-55. Bitterwolf J, Meinke A, Augustin M, Hein M. Breaking down out-of-distribution detection: Many methods based on OOD training data estimate a combination of the same core quantities. In: International Conference on Machine Learning. New York, NY: PMLR; 2022:2041-74. Wen B, Yao J, Feng S, Xu C, Tsvetkov Y, Howe B, et al. Know your limits: A survey of abstention in large language models. Trans Assoc Comput Linguist. 2025;13:529-56. Gandouz M, Holzmann H, Heider D. Machine learning with asymmetric abstention for biomedical decision-making. BMC Med Inform Decis Mak. 2021;21(1):294. Zhu Y, Nowak R. Efficient active learning with abstention. Adv Neural Inf Process Syst. 2022;35:35379-91. Nguyen VL, Hullermeier E. Reliable multilabel classification: Prediction with partial abstention. In: Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press; 2020;34(04):5264-71. Kompa B, Snoek J, Beam AL. Second opinion needed: Communicating uncertainty in medical machine learning. NPJ Digit Med. 2021;4(1):4. Gardner M. Abstention at the border. Va Law Rev. 2019;105(1):63-126. Schreuder N, Chzhen E. Classification with abstention but without disparities. In: Uncertainty in Artificial Intelligence. New York, NY: PMLR; 2021:1227-36. Swaminathan A, Lopez I, Wang W, Srivastava U, Tran E, Bhargava-Shah A, et al. Selective prediction for extracting unstructured clinical data. J Am Med Inform Assoc. 2024;31(1):188-97. Dvijotham K, Winkens J, Barsbey M, Ghaisas S, Stanforth R, Pawlowski N, et al. Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians. Nat Med. 2023;29(7):1814-20. Feng J, Sondhi A, Perry J, Simon N. Selective prediction-set models with coverage rate guarantees. Biometrics. 2023;79(2):811-25. Yoshikawa H, Okazaki N. Selective-LAMA: Selective prediction for confidence-aware evaluation of language models. In: Findings of the Association for Computational Linguistics: EACL. Stroudsburg, PA: Association for Computational Linguistics; 2023:2017-28. Dyer T, Lang M, Stice-Lawrence L. The evolution of 10-K textual disclosure: Evidence from latent Dirichlet allocation. J Account Econ. 2017;64(2-3):221-45.