{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:05:42Z","timestamp":1777421142348,"version":"3.51.4"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"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. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>\n            Just-in-Tim e (JIT) defect prediction has been proposed to help teams prioritize the limited resources on the most risky commits (or pull requests), yet it remains largely a black box, whose predictions are not explainable or actionable to practitioners. Thus, prior studies have applied various model-agnostic techniques to explain the predictions of JIT models. Yet, explanations generated from existing model-agnostic techniques are still not formally sound, robust, and actionable. In this article, we propose\n            <jats:sc>FoX<\/jats:sc>\n            , a\n            <jats:underline>Fo<\/jats:underline>\n            rmal e\n            <jats:underline>X<\/jats:underline>\n            plainer for JIT Defect Prediction, which builds on formal reasoning about the behavior of JIT defect prediction models and hence is able to provide provably correct explanations, which are additionally guaranteed to be minimal. Our experimental results show that\n            <jats:sc>FoX<\/jats:sc>\n            \u00a0is able to efficiently generate provably correct, robust, and actionable explanations, while existing model-agnostic techniques cannot. Our survey study with 54 software practitioners provides valuable insights into the usefulness and trustworthiness of our\n            <jats:sc>FoX<\/jats:sc>\n            \u00a0approach; 86% of participants agreed that our approach is useful, while 74% of participants found it trustworthy. Thus, this article serves as an important stepping stone towards trustable explanations for JIT models to help domain experts and practitioners better understand why a commit is predicted as defective and what to do to mitigate the risk.\n          <\/jats:p>","DOI":"10.1145\/3664809","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T11:33:29Z","timestamp":1715686409000},"page":"1-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["A Formal Explainer for Just-In-Time Defect Predictions"],"prefix":"10.1145","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4376-7266","authenticated-orcid":false,"given":"Jinqiang","family":"Yu","sequence":"first","affiliation":[{"name":"Data Science &amp; AI, Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7211-3491","authenticated-orcid":false,"given":"Michael","family":"Fu","sequence":"additional","affiliation":[{"name":"Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4535-2902","authenticated-orcid":false,"given":"Alexey","family":"Ignatiev","sequence":"additional","affiliation":[{"name":"Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5516-9984","authenticated-orcid":false,"given":"Chakkrit","family":"Tantithamthavorn","sequence":"additional","affiliation":[{"name":"Information Technology, Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2186-0459","authenticated-orcid":false,"given":"Peter","family":"Stuckey","sequence":"additional","affiliation":[{"name":"Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Amritanshu Agrawal and Tim Menzies. 2018. Is better data better than better data miners?: On the benefits of tuning SMOTE for defect prediction. In International Conference on Software Engineering (ICSE\u201918). 1050\u20131061.","DOI":"10.1145\/3180155.3180197"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion52605.2021.00056"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA336"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408795"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Di Chen Wei Fu Rahul Krishna and Tim Menzies. 2018. Applications of psychological science for actionable analytics. In Foundations of Software Engineering (ESEC\/FSE\u201918). 456\u2013467.","DOI":"10.1145\/3236024.3236050"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377812.3381386"},{"key":"e_1_3_2_10_2","volume-title":"Model Checking","author":"Clarke Edmund M.","year":"2018","unstructured":"Edmund M. Clarke, Orna Grumberg, Daniel Kroening, Doron A. Peled, and Helmut Veith. 2018. Model Checking. MIT Press."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/800157.805047"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2616306"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3183399.3183424"},{"key":"e_1_3_2_14_2","unstructured":"Adnan Darwiche and Auguste Hirth. 2020. On the reasons behind decisions. In European Conference on Artificial Intelligence (ECAI\u201920). 712\u2013720."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2008.923410"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593799"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Thong Hoang Hoa Khanh Dam Yasutaka Kamei David Lo and Naoyasu Ubayashi. 2019. DeepJIT: An end-to-end deep learning framework for just-in-time defect prediction. In International Conference on Mining Software Repositories (MSR\u201919). 34\u201345.","DOI":"10.1109\/MSR.2019.00016"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Thong Hoang Hong Jin Kang David Lo and Julia Lawall. 2020. CC2Vec: Distributed representations of code changes. In International Conference on Software Engineering (ICSE\u201920). 518\u2013529.","DOI":"10.1145\/3377811.3380361"},{"key":"e_1_3_2_19_2","article-title":"The inadequacy of shapley values for explainability","volume":"2302","author":"Huang Xuanxiang","year":"2023","unstructured":"Xuanxiang Huang and Joao Marques-Silva. 2023. The inadequacy of shapley values for explainability. CoRR abs\/2302.08160 (2023).","journal-title":"CoRR"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Alexey Ignatiev. 2020. Towards trustable explainable AI. In International Joint Conference on Artificial Intelligence (IJCAI\u201920). 5154\u20135158.","DOI":"10.24963\/ijcai.2020\/726"},{"key":"e_1_3_2_21_2","first-page":"335","volume-title":"AI*IA","author":"Ignatiev Alexey","year":"2020","unstructured":"Alexey Ignatiev, Nina Narodytska, Nicholas Asher, and Joao Marques-Silva. 2020. From contrastive to abductive explanations and back again. In AI*IA. 335\u2013355."},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Alexey Ignatiev Nina Narodytska and Joao Marques-Silva. 2019. Abduction-based explanations for machine learning models. In Association for the Advancement of Artificial Intelligence (AAAI\u201919). 1511\u20131519.","DOI":"10.1609\/aaai.v33i01.33011511"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Yacine Izza and Jo\u00e3o Marques-Silva. 2021. On explaining random forests with SAT. In International Joint Conference on Artificial Intelligence (IJCAI\u201921). 2584\u20132591.","DOI":"10.24963\/ijcai.2021\/356"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1592434.1592438"},{"key":"e_1_3_2_25_2","first-page":"166","article-title":"An empirical study of model-agnostic techniques for defect prediction models","author":"Jiarpakdee Jirayus","year":"2020","unstructured":"Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Hoa Khanh Dam, and John Grundy. 2020. An empirical study of model-agnostic techniques for defect prediction models. IEEE Transactions on Software Engineering (TSE) 48 (2020), 166\u2013185.","journal-title":"IEEE Transactions on Software Engineering (TSE)"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Jirayus Jiarpakdee Chakkrit Tantithamthavorn and John Grundy. 2021. Practitioners\u2019 perceptions of the goals and visual explanations of defect prediction models. In International Conference on Mining Software Repositories (MSR\u201921). 432\u2013443.","DOI":"10.1109\/MSR52588.2021.00055"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2012.70"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Chaiyakarn Khanan Worawit Luewichana Krissakorn Pruktharathikoon Jirayus Jiarpakdee Chakkrit Tantithamthavorn Morakot Choetkiertikul Chaiyong Ragkhitwetsagul and Thanwadee Sunetnanta. 2020. JITBot: An explainable just-in-time defect prediction bot. In International Conference on Automated Software Engineering (ASE\u201920). 1336\u20131339.","DOI":"10.1145\/3324884.3415295"},{"key":"e_1_3_2_30_2","unstructured":"Sunghun Kim Thomas Zimmermann E. James Whitehead Jr. and Andreas Zeller. 2007. Predicting faults from cached history. In International Conference on Software Engineering (ICSE\u201907). 489\u2013498."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84800-044-5_3"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Anvesh Komuravelli Arie Gurfinkel Sagar Chaki and Edmund M. Clarke. 2013. Automatic abstraction in SMT-based unbounded software model checking. In International Conference on Computer Aided Verification (CAV\u201913). 846\u2013862.","DOI":"10.1007\/978-3-642-39799-8_59"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09843-6"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Himabindu Lakkaraju and Osbert Bastani. 2020. \u201cHow do I fool you?\u201d: Manipulating user trust via misleading black box explanations. In AAAI\/ACM Conference on AI Ethics and Society (AIES\u201920). 79\u201385.","DOI":"10.1145\/3375627.3375833"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Chris Lewis Zhongpeng Lin Caitlin Sadowski Xiaoyan Zhu Rong Ou and E. James Whitehead Jr. 2013. Does bug prediction support human developers? Findings from a Google case study. In International Conference on Software Engineering (ICSE\u201913). 372\u2013381.","DOI":"10.1109\/ICSE.2013.6606583"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3073920"},{"key":"e_1_3_2_37_2","first-page":"4765","volume-title":"NIPS","author":"Lundberg Scott M.","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In NIPS. 4765\u20134774."},{"key":"e_1_3_2_38_2","unstructured":"Jo\u00e3o Marques-Silva Thomas Gerspacher Martin C. Cooper Alexey Ignatiev and Nina Narodytska. 2021. Explanations for monotonic classifiers. In International Conference on Machine Learning (ICML\u201921). 7469\u20137479."},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Joao Marques-Silva and Alexey Ignatiev. 2022. Delivering trustworthy AI through formal XAI. In Association for the Advancement of Artificial Intelligence (AAAI\u201919). 12342\u201312350.","DOI":"10.1609\/aaai.v36i11.21499"},{"key":"e_1_3_2_40_2","first-page":"412","article-title":"Are fix-inducing changes a moving target? A longitudinal case study of just-in-time defect prediction","author":"McIntosh Shane","year":"2017","unstructured":"Shane McIntosh and Yasutaka Kamei. 2017. Are fix-inducing changes a moving target? A longitudinal case study of just-in-time defect prediction. IEEE Transactions on Software Engineering (TSE) 44 (2017), 412\u2013428.","journal-title":"IEEE Transactions on Software Engineering (TSE)"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Nina Narodytska Aditya A. Shrotri Kuldeep S. Meel Alexey Ignatiev and Joao Marques-Silva. 2019. Assessing heuristic machine learning explanations with model counting. In Theory and Applications of Satisfiability Testing (SAT\u201919). 267\u2013278.","DOI":"10.1007\/978-3-030-24258-9_19"},{"key":"e_1_3_2_43_2","article-title":"Defect reduction planning (using TimeLIME)","author":"Peng Kewen","year":"2021","unstructured":"Kewen Peng and Tim Menzies. 2021. Defect reduction planning (using TimeLIME). IEEE Transactions on Software Engineering (TSE) 48 (2021), 2510\u20132525.","journal-title":"IEEE Transactions on Software Engineering (TSE)"},{"key":"e_1_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Chanathip Pornprasit and Chakkrit Tantithamthavorn. 2021. JITLine: A simpler better faster finer-grained just-in-time defect prediction. In International Conference on Mining Software Repositories (MSR\u201921). 369\u2013379.","DOI":"10.1109\/MSR52588.2021.00049"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Chanathip Pornprasit Chakkrit Tantithamthavorn Jirayus Jiarpakdee Michael Fu and Patanamon Thongtanunam. 2021. PyExplainer: Explaining the predictions of just-in-time defect models. In International Conference on Automated Software Engineering (ASE\u201920). 407\u2013418.","DOI":"10.1109\/ASE51524.2021.9678763"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3070559"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(87)90062-2"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Marco Tulio Ribeiro Sameer Singh and Carlos Guestrin. 2016. Why should I trust you?: Explaining the predictions of any classifier. In International Conference on Knowledge Discovery and Data Mining (KDD\u201916). 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Marco T\u00falio Ribeiro Sameer Singh and Carlos Guestrin. 2018. Anchors: High-precision model-agnostic explanations. In Association for the Advancement of Artificial Intelligence (AAAI\u201918). 1527\u20131535.","DOI":"10.1609\/aaai.v32i1.11491"},{"issue":"28","key":"e_1_3_2_50_2","first-page":"307","article-title":"A value of n-person games","volume":"2","author":"Shapley LLoyd S.","year":"1953","unstructured":"LLoyd S. Shapley. 1953. A value of n-person games. Contributions to the Theory of Games 2, 28 (1953), 307\u2013317.","journal-title":"Contributions to the Theory of Games"},{"key":"e_1_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Andy Shih Arthur Choi and Adnan Darwiche. 2018. A symbolic approach to explaining Bayesian network classifiers. In International Joint Conference on Artificial Intelligence (IJCAI\u201918). 5103\u20135111.","DOI":"10.24963\/ijcai.2018\/708"},{"key":"e_1_3_2_52_2","article-title":"Explainable software defect prediction: Are we there yet?","author":"Shin Jiho","year":"2021","unstructured":"Jiho Shin, Reem Aleithan, Jaechang Nam, Junjie Wang, and Song Wang. 2021. Explainable software defect prediction: Are we there yet? arXiv preprint arXiv:2111.10901 (2021).","journal-title":"arXiv preprint arXiv:2111.10901"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Dylan Slack Sophie Hilgard Emily Jia Sameer Singh and Himabindu Lakkaraju. 2020. Fooling LIME and SHAP: Adversarial attacks on post hoc explanation methods. In AAAI\/ACM Conference on AI Ethics and Society (AIES\u201920). 180\u2013186.","DOI":"10.1145\/3375627.3375830"},{"key":"e_1_3_2_54_2","unstructured":"Dylan Z. Slack Sophie Hilgard Sameer Singh and Himabindu Lakkaraju. 2021. Reliable post hoc explanations: Modeling uncertainty in explainability. In Conference on Neural Information Processing Systems (NeurIPS\u201921)."},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Jacek \u015aliwerski Thomas Zimmermann and Andreas Zeller. 2005. When do changes induce fixes? In International Conference on Mining Software Repositories (MSR\u201905). 1-\u20135.","DOI":"10.1145\/1083142.1083147"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2876537"},{"key":"e_1_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Chakkrit Tantithamthavorn and Jirayus Jiarpakdee. 2021. Explainable AI for software engineering. In International Conference on Automated Software Engineering (ASE\u201921). 1\u20132.","DOI":"10.1109\/ASE51524.2021.9678580"},{"key":"e_1_3_2_58_2","article-title":"Explainable AI for software engineering","author":"Tantithamthavorn Chakkrit","year":"2020","unstructured":"Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, and John Grundy. 2020. Explainable AI for software engineering. arXiv preprint arXiv:2012.01614 (2020).","journal-title":"arXiv preprint arXiv:2012.01614"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2021.3072088"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2584050"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2949568"},{"key":"e_1_3_2_62_2","article-title":"Predicting defective lines using a model-agnostic technique","author":"Wattanakriengkrai Supatsara","year":"2020","unstructured":"Supatsara Wattanakriengkrai, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Hideaki Hata, and Kenichi Matsumoto. 2020. Predicting defective lines using a model-agnostic technique. IEEE Transactions on Software Engineering (TSE) 48 (2020), 1480\u20131496.","journal-title":"IEEE Transactions on Software Engineering (TSE)"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/1852102.1852106"},{"key":"e_1_3_2_64_2","first-page":"51","article-title":"Actionable analytics for software engineering","author":"Yang Ye","year":"2017","unstructured":"Ye Yang, Davide Falessi, Tim Menzies, and Jairus Hihn. 2017. Actionable analytics for software engineering. IEEE Software 35 (2017), 51\u201353.","journal-title":"IEEE Software"},{"key":"e_1_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Suraj Yathish Jirayus Jiarpakdee Patanamon Thongtanunam and Chakkrit Tantithamthavorn. 2019. Mining software defects: Should we consider affected releases? In International Conference on Software Engineering (ICSE\u201919). 654\u2013665.","DOI":"10.1109\/ICSE.2019.00075"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.03380"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664809","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":65,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3664809"],"URL":"https:\/\/doi.org\/10.1145\/3664809","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,26]]},"assertion":[{"value":"2023-09-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}