{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:54:42Z","timestamp":1784044482731,"version":"3.55.0"},"reference-count":106,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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":["Empir Software Eng"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10664-025-10717-y","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T09:08:08Z","timestamp":1759136888000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards understanding the impact of data bugs on deep learning models in software engineering"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3584-0470","authenticated-orcid":false,"given":"Mehil B.","family":"Shah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3821-5990","authenticated-orcid":false,"given":"Mohammad Masudur","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-4173","authenticated-orcid":false,"given":"Foutse","family":"Khomh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"10717_CR1","unstructured":"(2024) GeeksforGeeks. Accessed on June 29, 2024. https:\/\/www.geeksforgeeks.org\/best-ides-for-machine-learning\/"},{"key":"10717_CR2","unstructured":"(2024) The guardian. https:\/\/www.theguardian.com\/technology\/2024\/apr\/26\/tesla-autopilot-fatal-crash"},{"key":"10717_CR3","unstructured":"(n.d.) Apache. https:\/\/issues.apache.org\/jira\/projects\/HADOOP\/issues"},{"issue":"1","key":"10717_CR4","doi-asserted-by":"publisher","first-page":"20220278","DOI":"10.1515\/comp-2022-0278","volume":"13","author":"A Amato","year":"2023","unstructured":"Amato A, Di Lecce V (2023) Data preprocessing impact on machine learning algorithm performance. Open Comput Sci 13(1):20220278","journal-title":"Open Comput Sci"},{"key":"10717_CR5","unstructured":"Amodei D, Ananthanarayanan S, Anubhai R, Bai J, Battenberg E, Case C, Casper J, Catanzaro B, Cheng Q, Chen G et\u00a0al (2016) Deep speech 2: end-to-end speech recognition in English and Mandarin. In: International conference on machine learning, pp 173\u2013182. PMLR"},{"issue":"3","key":"10717_CR6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1002\/stvr.1486","volume":"24","author":"A Arcuri","year":"2014","unstructured":"Arcuri A, Briand L (2014) A hitchhiker\u2019s guide to statistical tests for assessing randomized algorithms in software engineering. Softw Test Verification Reliab 24(3):219\u2013250","journal-title":"Softw Test Verification Reliab"},{"key":"10717_CR7","doi-asserted-by":"crossref","unstructured":"Arpteg A, Brinne B, Crnkovic-Friis L, Bosch J (2018) Software engineering challenges of deep learning. In: 2018 44th Euromicro conference on software engineering and advanced applications (SEAA), pp 50\u201359. IEEE","DOI":"10.1109\/SEAA.2018.00018"},{"key":"10717_CR8","unstructured":"Cao S, Sun X, Widyasari R, Lo D, Wu X, Bo L, Zhang J, Li B, Liu W,\u00a0Wu D et\u00a0al (2024) A systematic literature review on explainability for machine\/deep learning-based software engineering research. arXiv:2401.14617"},{"issue":"7","key":"10717_CR9","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/TSE.2018.2792473","volume":"45","author":"M Choetkiertikul","year":"2018","unstructured":"Choetkiertikul M, Dam HK, Tran T, Pham T, Ghose A, Menzies T (2018) A deep learning model for estimating story points. IEEE Trans Softw Eng 45(7):637\u2013656","journal-title":"IEEE Trans Softw Eng"},{"issue":"2","key":"10717_CR10","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s10515-024-00453-w","volume":"31","author":"P-O C\u00f4t\u00e9","year":"2024","unstructured":"C\u00f4t\u00e9 P-O, Nikanjam A, Ahmed N, Humeniuk D, Khomh F (2024) Data cleaning and machine learning: a systematic literature review. Autom Softw Eng 31(2):54","journal-title":"Autom Softw Eng"},{"issue":"3","key":"10717_CR11","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1109\/TSE.2022.3171202","volume":"49","author":"R Croft","year":"2022","unstructured":"Croft R, Xie Y, Babar MA (2022) Data preparation for software vulnerability prediction: a systematic literature review. IEEE Trans Softw Eng 49(3):1044\u20131063","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR12","doi-asserted-by":"crossref","unstructured":"Croft R, Babar MA, Kholoosi MM (2023) Data quality for software vulnerability datasets. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp 121\u2013133. IEEE","DOI":"10.1109\/ICSE48619.2023.00022"},{"key":"10717_CR13","doi-asserted-by":"crossref","unstructured":"Cummins C, Petoumenos P, Murray A, Leather H (2018) Compiler fuzzing through deep learning. In: Proceedings of the 27th ACM SIGSOFT international symposium on software testing and analysis, pp 95\u2013105","DOI":"10.1145\/3213846.3213848"},{"key":"10717_CR14","doi-asserted-by":"crossref","unstructured":"Ding Y, Fu Y, Ibrahim O, Sitawarin C, Chen X, Alomair B, Wagner D, Ray B, Chen Y (2024) Vulnerability detection with code language models: how far are we? arXiv:2403.18624","DOI":"10.1109\/ICSE55347.2025.00038"},{"key":"10717_CR15","first-page":"2019","volume":"1\u201326","author":"Y Fan","year":"2019","unstructured":"Fan Y, Xia X, Costa DA, Lo D, Hassan AE, Li S (2019) The impact of changes mislabeled by szz on just-in-time defect prediction. IEEE Trans Softw Eng 1\u201326:2019","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR16","doi-asserted-by":"crossref","unstructured":"Fan J,\u00a0Li Y, Wang S, Nguyen TN (2020) Ac\/c++ code vulnerability dataset with code changes and cve summaries. In: Proceedings of the 17th international conference on mining software repositories, pp 508\u2013512","DOI":"10.1145\/3379597.3387501"},{"issue":"5","key":"10717_CR17","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","volume":"25","author":"B Fr\u00e9nay","year":"2013","unstructured":"Fr\u00e9nay B, Verleysen M (2013) Classification in the presence of label noise: a survey. IEEE Trans Neural Netw Learn Syst 25(5):845\u2013869","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10717_CR18","unstructured":"Fr\u00e9nay B, Kab\u00e1n A et\u00a0al (2014) A comprehensive introduction to label noise. In: ESANN. Citeseer"},{"issue":"2","key":"10717_CR19","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TSE.2022.3158252","volume":"49","author":"M Fu","year":"2022","unstructured":"Fu M, Tantithamthavorn C (2022) Gpt2sp: a transformer-based agile story point estimation approach. IEEE Trans Softw Eng 49(2):611\u2013625","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR20","doi-asserted-by":"crossref","unstructured":"Fu M, Tantithamthavorn C (2022) Linevul: a transformer-based line-level vulnerability prediction. In: Proceedings of the 19th international conference on mining software repositories, pp 608\u2013620","DOI":"10.1145\/3524842.3528452"},{"key":"10717_CR21","doi-asserted-by":"crossref","unstructured":"Gao S, Wen X-C, Gao C, Wang W, Zhang H, Lyu MR (2023) What makes good in-context demonstrations for code intelligence tasks with llms? In: 2023 38th IEEE\/ACM international conference on Automated Software Engineering (ASE), pp 761\u2013773. IEEE","DOI":"10.1109\/ASE56229.2023.00109"},{"key":"10717_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111537","volume":"195","author":"G Giray","year":"2023","unstructured":"Giray G, Bennin KE, K\u00f6ksal \u00d6, Babur \u00d6, Tekinerdogan B (2023) On the use of deep learning in software defect prediction. J Syst Softw 195:111537","journal-title":"J Syst Softw"},{"key":"10717_CR23","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 249\u2013256. JMLR workshop and conference proceedings"},{"key":"10717_CR24","unstructured":"Goodfellow I (2016) Deep learning, volume 196. MIT press"},{"issue":"3","key":"10717_CR25","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1002\/rob.21918","volume":"37","author":"S Grigorescu","year":"2020","unstructured":"Grigorescu S, Trasnea B, Cocias T, Macesanu G (2020) A survey of deep learning techniques for autonomous driving. J Field Robot 37(3):362\u2013386","journal-title":"J Field Robot"},{"key":"10717_CR26","doi-asserted-by":"crossref","unstructured":"Gros D, Sezhiyan H, Devanbu P, Yu Z (2020) Code to comment \u201ctranslation\" data, metrics, baselining & evaluation. In: Proceedings of the 35th IEEE\/ACM international conference on automated software engineering, pp 746\u2013757","DOI":"10.1145\/3324884.3416546"},{"key":"10717_CR27","doi-asserted-by":"publisher","unstructured":"Guo Y, Gao X, Zhang Z, Chan WK,\u00a0Jiang B (2023) A study on the impact of pre-trained model on just-in-time defect prediction. In: 2023 IEEE 23rd international conference on software Quality, Reliability, and Security (QRS), pp 105\u2013116. https:\/\/doi.org\/10.1109\/QRS60937.2023.00020","DOI":"10.1109\/QRS60937.2023.00020"},{"key":"10717_CR28","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez L\u00f3pez JA, Chen B, Sharma T, Varr\u00f3 D (2024) On inter-dataset code duplication and data leakage in large language models. arXiv:2401.07930","DOI":"10.1109\/TSE.2024.3504286"},{"key":"10717_CR29","doi-asserted-by":"crossref","unstructured":"He J, Xu L, Yan M, Xia X, Lei Y (2020) Duplicate bug report detection using dual-channel convolutional neural networks. In: Proceedings of the 28th international conference on program comprehension, pp 117\u2013127","DOI":"10.1145\/3387904.3389263"},{"key":"10717_CR30","doi-asserted-by":"crossref","unstructured":"Hoang T, Dam HK, Kamei Y, Lo D, Ubayashi N (2019) Deepjit: an end-to-end deep learning framework for just-in-time defect prediction. In: 2019 IEEE\/ACM 16th International conference on Mining Software Repositories (MSR), pp 34\u201345. IEEE","DOI":"10.1109\/MSR.2019.00016"},{"issue":"FSE","key":"10717_CR31","doi-asserted-by":"publisher","first-page":"1471","DOI":"10.1145\/3660773","volume":"1","author":"SB Hossain","year":"2024","unstructured":"Hossain SB, Jiang N, Zhou Q, Li X, Chiang W-H, Lyu Y, Nguyen H, Tripp O (2024) A deep dive into large language models for automated bug localization and repair. Proc ACM on Softw Eng 1(FSE):1471\u20131493","journal-title":"Proc ACM on Softw Eng"},{"key":"10717_CR32","doi-asserted-by":"publisher","unstructured":"Humbatova N, Jahangirova G, Bavota G, Riccio V, Stocco A, Tonella P (2020) Taxonomy of real faults in deep learning systems. In: Proceedings of the ACM\/IEEE 42nd international conference on software engineering, pp 1110\u20131121. Seoul South Korea. ACM. https:\/\/doi.org\/10.1145\/3377811.3380395. https:\/\/dl.acm.org\/doi\/10.1145\/3377811.3380395","DOI":"10.1145\/3377811.3380395"},{"key":"10717_CR33","doi-asserted-by":"crossref","unstructured":"Humbatova N, Jahangirova G, Tonella P (2021) Deepcrime: mutation testing of deep learning systems based on real faults. In: Proceedings of the 30th ACM SIGSOFT international symposium on software testing and analysis, pp 67\u201378","DOI":"10.1145\/3460319.3464825"},{"key":"10717_CR34","doi-asserted-by":"crossref","unstructured":"Irsan IC, Zhang T, Thung F, Kim K, Lo D (2023) Multi-modal api recommendation. In: 2023 IEEE international conference on Software Analysis, Evolution and Reengineering (SANER), pp 272\u2013283. IEEE","DOI":"10.1109\/SANER56733.2023.00034"},{"key":"10717_CR35","doi-asserted-by":"publisher","unstructured":"Islam MdJ, Nguyen G, Pan R, Rajan H (2019) A comprehensive study on deep learning bug characteristics. In: Proceedings of the 2019 27th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering, pp 510\u2013520. Tallinn Estonia. ACM. https:\/\/doi.org\/10.1145\/3338906.3338955. https:\/\/dl.acm.org\/doi\/10.1145\/3338906.3338955","DOI":"10.1145\/3338906.3338955"},{"issue":"6","key":"10717_CR36","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/TSE.2012.70","volume":"39","author":"Y Kamei","year":"2012","unstructured":"Kamei Y, Shihab E, Adams B, Hassan AE, Mockus A, Sinha A, Ubayashi N (2012) A large-scale empirical study of just-in-time quality assurance. IEEE Trans Softw Eng 39(6):757\u2013773","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR37","doi-asserted-by":"crossref","unstructured":"Keshavarz H, Nagappan M (2022) Apachejit: a large dataset for just-in-time defect prediction. In: Proceedings of the 19th international conference on mining software repositories, pp 191\u2013195","DOI":"10.1145\/3524842.3527996"},{"key":"10717_CR38","doi-asserted-by":"crossref","unstructured":"Kim S, Zhang H, Wu R, Gong L (2011) Dealing with noise in defect prediction. In: Proceedings of the 33rd international conference on software engineering, pp 481\u2013490","DOI":"10.1145\/1985793.1985859"},{"key":"10717_CR39","unstructured":"Koh PW, Liang P (2017) Understanding black-box predictions via influence functions. In: International conference on machine learning, pp 1885\u20131894. PMLR"},{"key":"10717_CR40","doi-asserted-by":"crossref","unstructured":"Lai TD (2021) Towards the generation of machine learning defect reports. In: 2021 36th IEEE\/ACM International conference on Automated Software Engineering (ASE), pp 1038\u20131042. IEEE","DOI":"10.1109\/ASE51524.2021.9678592"},{"key":"10717_CR41","doi-asserted-by":"crossref","unstructured":"Lazar A, Ritchey S, Sharif B (2014) Generating duplicate bug datasets. In: Proceedings of the 11th working conference on mining software repositories, pp 392\u2013395","DOI":"10.1145\/2597073.2597128"},{"key":"10717_CR42","doi-asserted-by":"crossref","unstructured":"LeCun Y, Bottou L, Orr GB, M\u00fcller K-R (2002) Efficient backprop. In: Neural networks: tricks of the trade, pp 9\u201350. Springer","DOI":"10.1007\/3-540-49430-8_2"},{"issue":"4","key":"10717_CR43","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1016\/j.jesp.2013.03.013","volume":"49","author":"C Leys","year":"2013","unstructured":"Leys C, Ley C, Klein O, Bernard P, Licata L (2013) Detecting outliers: do not use standard deviation around the mean, use absolute deviation around the median. J Exp Soc Psychol 49(4):764\u2013766","journal-title":"J Exp Soc Psychol"},{"issue":"8","key":"10717_CR44","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1038\/s42256-022-00516-1","volume":"4","author":"W Liang","year":"2022","unstructured":"Liang W, Tadesse GA, Ho D, Fei-Fei L, Zaharia M, Zhang C, Zou J (2022) Advances, challenges and opportunities in creating data for trustworthy ai. Nat Mach Intell 4(8):669\u2013677","journal-title":"Nat Mach Intell"},{"key":"10717_CR45","doi-asserted-by":"crossref","unstructured":"Li L,\u00a0Feng H, Zhuang W,\u00a0Meng N, Ryder B (2017) Cclearner: a deep learning-based clone detection approach. In: 2017 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp 249\u2013260. IEEE","DOI":"10.1109\/ICSME.2017.46"},{"key":"10717_CR46","doi-asserted-by":"crossref","unstructured":"Li Z, Pan M,\u00a0Pei Y, Zhang T, Wang L, Li X (2022) Robust learning of deep predictive models from noisy and imbalanced software engineering datasets. In: Proceedings of the 37th IEEE\/ACM international conference on automated software engineering, pp 1\u201313","DOI":"10.1145\/3551349.3556941"},{"issue":"9","key":"10717_CR47","first-page":"1811","volume":"47","author":"H Liu","year":"2019","unstructured":"Liu H, Jin J, Xu Z, Zou Y, Bu Y, Zhang L (2019) Deep learning based code smell detection. IEEE Trans Softw Eng 47(9):1811\u20131837","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR48","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1016\/j.procs.2022.11.349","volume":"214","author":"Y Liu","year":"2022","unstructured":"Liu Y, Zhang W, Qin G, Zhao J (2022) A comparative study on the effect of data imbalance on software defect prediction. Proc Comput Sci 214:1603\u20131616","journal-title":"Proc Comput Sci"},{"key":"10717_CR49","doi-asserted-by":"publisher","unstructured":"Liu L, Liu X, Gao J, Chen W, Han J (2020) Understanding the difficulty of training transformers. In: Webber B, Cohn T, He Y, Liu Y (eds) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 5747\u20135763, Online, November 2020. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.463. https:\/\/aclanthology.org\/2020.emnlp-main.463","DOI":"10.18653\/v1\/2020.emnlp-main.463"},{"key":"10717_CR50","unstructured":"Li G,\u00a0Yin L, Ji J, Niu W, Qin M, Ren B, Guo L, Liu S, Ma X (2024) Neurrev: train better sparse neural network practically via neuron revitalization. In: 12th International conference on learning representations, ICLR 2024"},{"issue":"7","key":"10717_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3664606","volume":"33","author":"W Ma","year":"2024","unstructured":"Ma W, Liu S, Zhao M, Xie X, Wang W, Hu Q, Zhang J, Liu Y (2024) Unveiling code pre-trained models: investigating syntax and semantics capacities. ACM Trans Softw Eng Methodol 33(7):1\u201329","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"10717_CR52","doi-asserted-by":"crossref","unstructured":"Mahbub P, Shuvo O,\u00a0Masudur Rahman M (2023) Defectors: a large, diverse python dataset for defect prediction. In: 2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR), pp 393\u2013397. IEEE","DOI":"10.1109\/MSR59073.2023.00085"},{"key":"10717_CR53","doi-asserted-by":"crossref","unstructured":"Mahmood Z, Bowes D, Lane PCR, Hall T (2015) What is the impact of imbalance on software defect prediction performance? In: Proceedings of the 11th international conference on predictive models and data analytics in software engineering, pp 1\u20134","DOI":"10.1145\/2810146.2810150"},{"key":"10717_CR54","doi-asserted-by":"crossref","unstructured":"Mao D, Chen L, Zhang L (2019) An extensive study on cross-project predictive mutation testing. In: 2019 12th IEEE Conference on Software Testing, Validation and Verification (ICST), pp 160\u2013171. IEEE","DOI":"10.1109\/ICST.2019.00025"},{"key":"10717_CR55","doi-asserted-by":"crossref","unstructured":"Ma M, Zhang S, Pei D, Huang X, Dai H (2018) Robust and rapid adaption for concept drift in software system anomaly detection. In: 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE), pp 13\u201324. IEEE","DOI":"10.1109\/ISSRE.2018.00013"},{"key":"10717_CR56","doi-asserted-by":"crossref","unstructured":"McIntosh S, Kamei Y (2018) Are fix-inducing changes a moving target? A longitudinal case study of just-in-time defect prediction. In: Proceedings of the 40th international conference on software engineering, pp 560\u2013560","DOI":"10.1145\/3180155.3182514"},{"key":"10717_CR57","doi-asserted-by":"crossref","unstructured":"Messaoud MB, Miladi A, Jenhani I, Mkaouer MW, Ghadhab L (2022) Duplicate bug report detection using an attention-based neural language model. IEEE Trans Reliab","DOI":"10.1109\/TR.2022.3193645"},{"issue":"2","key":"10717_CR58","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1109\/TR.2022.3193645","volume":"72","author":"MB Messaoud","year":"2023","unstructured":"Messaoud MB, Miladi A, Jenhani I, Mkaouer MW, Ghadhab L (2023) Duplicate bug report detection using an attention-based neural language model. IEEE Trans Reliab 72(2):846\u2013858. https:\/\/doi.org\/10.1109\/TR.2022.3193645","journal-title":"IEEE Trans Reliab"},{"key":"10717_CR59","doi-asserted-by":"publisher","unstructured":"Mondal S,\u00a0Rahman M, Roy CK (2024) Can we identify stack overflow questions requiring code snippets? Investigating the cause & effect of missing code snippets. In: 2024 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), pp 764\u2013775. Los Alamitos, CA, USA. IEEE Computer Society. https:\/\/doi.ieeecomputersociety.org\/10.1109\/SANER60148.2024.00083. https:\/\/doi.org\/10.1109\/SANER60148.2024.00083","DOI":"10.1109\/SANER60148.2024.00083"},{"key":"10717_CR60","doi-asserted-by":"crossref","unstructured":"Mu F, Chen X, Shi L, Wang S, Wang Q (2023) Developer-intent driven code comment generation. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp 768\u2013780. IEEE","DOI":"10.1109\/ICSE48619.2023.00073"},{"key":"10717_CR61","unstructured":"Nagarajan P, Warnell G, Stone P (2018) The impact of nondeterminism on reproducibility in deep reinforcement learning"},{"key":"10717_CR62","unstructured":"Neal B, Mittal S, Baratin A, Tantia V, Scicluna M, Lacoste-Julien S, Mitliagkas I (2018) A modern take on the bias-variance tradeoff in neural networks. arXiv:1810.08591"},{"key":"10717_CR63","doi-asserted-by":"crossref","unstructured":"Nie X, Li N, Wang K, Wang S, Luo X, Wang H (2023) Understanding and tackling label errors in deep learning-based vulnerability detection (experience paper). In: Proceedings of the 32nd ACM SIGSOFT international symposium on software testing and analysis, pp 52\u201363","DOI":"10.1145\/3597926.3598037"},{"key":"10717_CR64","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1613\/jair.1.12125","volume":"70","author":"C Northcutt","year":"2021","unstructured":"Northcutt C, Jiang L, Chuang I (2021) Confident learning: estimating uncertainty in dataset labels. J Artif Intell Res 70:1373\u20131411","journal-title":"J Artif Intell Res"},{"issue":"5","key":"10717_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-024-10518-9","volume":"29","author":"YE Ouatiti","year":"2024","unstructured":"Ouatiti YE, Sayagh M, Kerzazi N, Adams B, Hassan AE (2024) The impact of concept drift and data leakage on log level prediction models. Empir Softw Eng 29(5):1\u201337","journal-title":"Empir Softw Eng"},{"key":"10717_CR66","unstructured":"Pascanu R (2013) On the difficulty of training recurrent neural networks. arXiv:1211.5063"},{"key":"10717_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00265-020-02916-y","volume":"74","author":"MQR Pembury Smith","year":"2020","unstructured":"Pembury Smith MQR, Ruxton GD (2020) Effective use of the Mcnemar test. Behav Ecol Sociobiol 74:1\u20139","journal-title":"Behav Ecol Sociobiol"},{"issue":"1","key":"10717_CR68","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/TSE.2022.3144348","volume":"49","author":"C Pornprasit","year":"2022","unstructured":"Pornprasit C, Tantithamthavorn CK (2022) Deeplinedp: towards a deep learning approach for line-level defect prediction. IEEE Trans Softw Eng 49(1):84\u201398","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR69","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10664-008-9102-8","volume":"14","author":"P Runeson","year":"2009","unstructured":"Runeson P, H\u00f6st M (2009) Guidelines for conducting and reporting case study research in software engineering. Empir Softw Eng 14:131\u2013164","journal-title":"Empir Softw Eng"},{"key":"10717_CR70","doi-asserted-by":"crossref","unstructured":"Sambasivan N, Kapania S, Highfill H, Akrong D, Paritosh P, Aroyo LM (2021) \u201ceveryone wants to do the model work, not the data work\u201d: data cascades in high-stakes ai. In: Proceedings of the 2021 CHI conference on human factors in computing systems, pp 1\u201315","DOI":"10.1145\/3411764.3445518"},{"key":"10717_CR71","unstructured":"Schelter S, Biessmann F, Januschowski T, Salinas D, Seufert S, Szarvas G (2015) On challenges in machine learning model management"},{"key":"10717_CR72","doi-asserted-by":"crossref","unstructured":"Selvaraju R, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"10717_CR73","doi-asserted-by":"crossref","unstructured":"Shah M (2025) Towards understanding the impact of data bugs on deep learning models in software engineering. https:\/\/zenodo.org\/records\/15270651","DOI":"10.1007\/s10664-025-10717-y"},{"issue":"1","key":"10717_CR74","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10664-024-10579-w","volume":"30","author":"MB Shah","year":"2025","unstructured":"Shah MB, Rahman MM, Khomh F (2025) Towards enhancing the reproducibility of deep learning bugs: an empirical study. Empir Softw Eng 30(1):23","journal-title":"Empir Softw Eng"},{"key":"10717_CR75","doi-asserted-by":"crossref","unstructured":"Shi L, Mu F, Chen X, Wang S, Wang J,\u00a0Yang Y,\u00a0Li G, Xia X, Wang Q (2022) Are we building on the rock? On the importance of data preprocessing for code summarization. In: Proceedings of the 30th ACM joint European software engineering conference and symposium on the foundations of software engineering, pp 107\u2013119","DOI":"10.1145\/3540250.3549145"},{"issue":"12","key":"10717_CR76","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1109\/TSE.2018.2836442","volume":"45","author":"Q Song","year":"2018","unstructured":"Song Q, Guo Y, Shepperd M (2018) A comprehensive investigation of the role of imbalanced learning for software defect prediction. IEEE Trans Softw Eng 45(12):1253\u20131269","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR77","unstructured":"Stevens WR, Fenner B, Rudoff AM (2013) UNIX network programming. 1: the sockets networking API \/ W. Stevens R, Fenner B, Rudoff AM. Addison-Wesley professional computing series. Addison-Wesley, Boston, 3rd ed edition"},{"key":"10717_CR78","unstructured":"Storm L (2020) Unstable gradients in deep neural nets"},{"issue":"3","key":"10717_CR79","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/s00787-010-0087-7","volume":"19","author":"M Szumilas","year":"2010","unstructured":"Szumilas M (2010) Explaining odds ratios. J Can Acad Child Adolesc Psychiatry 19(3):227","journal-title":"J Can Acad Child Adolesc Psychiatry"},{"key":"10717_CR80","doi-asserted-by":"crossref","unstructured":"Tantithamthavorn C, McIntosh S, Hassan AE, Ihara A, Matsumoto K (2015) The impact of mislabelling on the performance and interpretation of defect prediction models. In: 2015 IEEE\/ACM 37th IEEE international conference on software engineering, vol\u00a01, pp 812\u2013823. IEEE","DOI":"10.1109\/ICSE.2015.93"},{"key":"10717_CR81","doi-asserted-by":"crossref","unstructured":"Tian H, Liu K, Kabor\u00e9 AK, Koyuncu A,\u00a0Li L, Klein J, Bissyand\u00e9 TF (2020) Evaluating representation learning of code changes for predicting patch correctness in program repair. In: Proceedings of the 35th IEEE\/ACM international conference on automated software engineering, pp 981\u2013992","DOI":"10.1145\/3324884.3416532"},{"key":"10717_CR82","doi-asserted-by":"crossref","unstructured":"Tufano R, Masiero S, Mastropaolo A, Pascarella L, Poshyvanyk D, Bavota G (2022) Using pre-trained models to boost code review automation. In: Proceedings of the 44th international conference on software engineering, pp 2291\u20132302","DOI":"10.1145\/3510003.3510621"},{"key":"10717_CR83","unstructured":"Tukey JW (1977) Exploratory data analysis. Reading\/Addison-Wesley"},{"key":"10717_CR84","unstructured":"Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11)"},{"key":"10717_CR85","unstructured":"Vaswani A (2017) Attention is all you need. Advances in neural information processing systems"},{"key":"10717_CR86","doi-asserted-by":"crossref","unstructured":"Vitale A, Mastropaolo A, Oliveto R,\u00a0Di Penta M, Scalabrino S (2025) Optimizing datasets for code summarization: is code-comment coherence enough? arXiv:2502.07611","DOI":"10.1109\/ICPC66645.2025.00033"},{"key":"10717_CR87","unstructured":"Wakabayashi D (2018) Self-driving uber car kills pedestrian in Arizona, where robots roam. https:\/\/www.nytimes.com\/2018\/03\/19\/technology\/uber-driverless-fatality.html"},{"key":"10717_CR88","doi-asserted-by":"publisher","unstructured":"Wang W, Li Y, Li A, Zhang J, Ma W, Liu Y (2024) An empirical study on noisy label learning for program understanding. In: Proceedings of the IEEE\/ACM 46th international conference on software engineering, ICSE \u201924, New York, NY, USA. Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3597503.3639217","DOI":"10.1145\/3597503.3639217"},{"key":"10717_CR89","doi-asserted-by":"crossref","unstructured":"Wang X, Liu J,\u00a0Li L, Chen X, Liu X, Wu H (2020) Detecting and explaining self-admitted technical debts with attention-based neural networks. In: Proceedings of the 35th IEEE\/ACM international conference on automated software engineering, pp 871\u2013882","DOI":"10.1145\/3324884.3416583"},{"key":"10717_CR90","unstructured":"Weights, Biases (2021) Weights and biases: an ai developer platform. https:\/\/wandb.ai\/site. [Online; Accessed 21 Feb 2024]"},{"issue":"3","key":"10717_CR91","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1080\/00031305.2014.917055","volume":"68","author":"PH Westfall","year":"2014","unstructured":"Westfall PH (2014) Kurtosis as peakedness, 1905\u20132014. rip. Am Stat 68(3):191\u2013195","journal-title":"Am Stat"},{"issue":"12","key":"10717_CR92","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.14778\/3415478.3415562","volume":"13","author":"SE Whang","year":"2020","unstructured":"Whang SE, Lee J-G (2020) Data collection and quality challenges for deep learning. Proc VLDB Endow 13(12):3429\u20133432","journal-title":"Proc VLDB Endow"},{"key":"10717_CR93","unstructured":"Williams E, Ryoo AH-W, Jiralerspong T, Payeur A, Perich MG, Mazzucato L, Lajoie G (2025) Expressivity of neural networks with random weights and learned biases. ICLR 2025"},{"issue":"7","key":"10717_CR94","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1109\/TSE.2021.3063727","volume":"48","author":"X Wu","year":"2021","unstructured":"Wu X, Zheng W, Xia X, Lo D (2021) Data quality matters: a case study on data label correctness for security bug report prediction. IEEE Trans Softw Eng 48(7):2541\u20132556","journal-title":"IEEE Trans Softw Eng"},{"key":"10717_CR95","doi-asserted-by":"crossref","unstructured":"Xu Z, Guo S, Wang Y, Chen R, Li H, Li X,\u00a0Jiang H (2024) Code comment inconsistency detection based on confidence learning. IEEE Trans Softw Eng","DOI":"10.1109\/TSE.2024.3358489"},{"key":"10717_CR96","doi-asserted-by":"crossref","unstructured":"Xu S, Yao Y, Xu F, Gu T, Xu J, Ma X (2023) Data quality matters: a case study of obsolete comment detection. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp 781\u2013793. IEEE","DOI":"10.1109\/ICSE48619.2023.00074"},{"key":"10717_CR97","doi-asserted-by":"publisher","unstructured":"Yang Y, Xia X, Lo D, Grundy J (2022) A survey on deep learning for software engineering. ACM Comput Surv 54(10s). https:\/\/doi.org\/10.1145\/3505243","DOI":"10.1145\/3505243"},{"key":"10717_CR98","doi-asserted-by":"publisher","unstructured":"Yatish S, Jiarpakdee J, Thongtanunam P, Tantithamthavorn C (2019) Mining software defects: should we consider affected releases? In: 2019 IEEE\/ACM 41st International Conference on Software Engineering (ICSE), pp 654\u2013665. https:\/\/doi.org\/10.1109\/ICSE.2019.00075","DOI":"10.1109\/ICSE.2019.00075"},{"key":"10717_CR99","unstructured":"Ye C, Yang Y, Fermuller C, Aloimonos Y (2017) On the importance of consistency in training deep neural networks. arXiv:1708.00631"},{"key":"10717_CR100","unstructured":"Yin RK (2009) Case study research: design and methods, volume\u00a05. Sage"},{"key":"10717_CR101","doi-asserted-by":"crossref","unstructured":"Yin Y, Feng Y, Weng S, Liu Z, Yao Y, Zhang Y, Zhao Z, Chen Z (2023) Dynamic data fault localization for deep neural networks. In: Proceedings of the 31st ACM joint European software engineering conference and symposium on the foundations of software engineering, pp 1345\u20131357","DOI":"10.1145\/3611643.3616345"},{"key":"10717_CR102","doi-asserted-by":"publisher","unstructured":"Zeng Z, Zhang Y, Zhang H, Zhang L (2021) Deep just-in-time defect prediction: how far are we? In: Proceedings of the 30th ACM SIGSOFT international symposium on software testing and analysis, ISSTA 2021, pp 427\u2013438, New York, NY, USA. Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3460319.3464819","DOI":"10.1145\/3460319.3464819"},{"issue":"4","key":"10717_CR103","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3576042","volume":"32","author":"T Zhang","year":"2023","unstructured":"Zhang T, Han DG, Vinayakarao V, Irsan IC, Xu B, Thung F, Lo D, Jiang L (2023) Duplicate bug report detection: how far are we? ACM Trans Softw Eng Methodol 32(4):1\u201332","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"10717_CR104","unstructured":"Zhang Y, Saxe A, Latham PE (2024) When are bias-free relu networks like linear networks? arXiv:2406.12615"},{"key":"10717_CR105","doi-asserted-by":"crossref","unstructured":"Zhang J,\u00a0Wang X, Zhang H, Sun H, Pu Y, Liu X (2020) Learning to handle exceptions. In: Proceedings of the 35th IEEE\/ACM international conference on automated software engineering, pp 29\u201341","DOI":"10.1145\/3324884.3416568"},{"key":"10717_CR106","unstructured":"Zhou Y, Liu S, Siow J, Du X, Liu Y (2019) Devign: effective vulnerability identification by learning comprehensive program semantics via graph neural networks. Advances in neural information processing systems, vol 32"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10717-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10717-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10717-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T02:40:59Z","timestamp":1762310459000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10717-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":106,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10717"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10717-y","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"18 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors also declare they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}}],"article-number":"168"}}