{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:41:35Z","timestamp":1765233695941,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"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":[],"published-print":{"date-parts":[[2023,11,13]]},"DOI":"10.1145\/3631802.3631808","type":"proceedings-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T12:45:51Z","timestamp":1707223551000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Common Errors in Machine Learning Projects: A Second Look"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7774-3167","authenticated-orcid":false,"given":"Renato Magela","family":"Zimmermann","sequence":"first","affiliation":[{"name":"University of Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6611-2265","authenticated-orcid":false,"given":"Sonya","family":"Allin","sequence":"additional","affiliation":[{"name":"University of Toronto Mississauga, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7302-6530","authenticated-orcid":false,"given":"Lisa","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Toronto Mississauga, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,2,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[1] 2023. https:\/\/www.anaconda.com\/blog\/state-of-data-science-2022"},{"key":"e_1_3_2_1_2_1","unstructured":"2023. Kaggle. https:\/\/kaggle.com\/"},{"volume-title":"Why is developing machine learning applications challenging? A study on Stack Overflow posts. In 2019 acm\/ieee international symposium on empirical software engineering and measurement (esem)","author":"Alshangiti Moayad","key":"e_1_3_2_1_3_1","unstructured":"Moayad Alshangiti, Hitesh Sapkota, Pradeep\u00a0K. Murukannaiah, Xumin Liu, and Qi Yu. 2019. Why is developing machine learning applications challenging? A study on Stack Overflow posts. In 2019 acm\/ieee international symposium on empirical software engineering and measurement (esem). IEEE, 1\u201311."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3430665.3456332"},{"volume-title":"Evaluating the quality of learning: The SOLO taxonomy (Structure of the Observed Learning Outcome)","author":"Biggs B.","key":"e_1_3_2_1_5_1","unstructured":"John\u00a0B. Biggs and Kevin\u00a0F. Collis. 2014. Evaluating the quality of learning: The SOLO taxonomy (Structure of the Observed Learning Outcome). Academic Press."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3304221.3319771"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502289"},{"key":"e_1_3_2_1_8_1","volume-title":"URL: https:\/\/openai. com\/blog\/chatgpt (Last accessed: 17.02. 2023)","author":"Introducing","year":"2023","unstructured":"Introducing ChatGPT. 2023. OpenAI. URL: https:\/\/openai. com\/blog\/chatgpt (Last accessed: 17.02. 2023) (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2538862.2538966"},{"key":"e_1_3_2_1_10_1","volume-title":"Attitudes towards Risk and Their Role in Risk Creation in the Field of Healthcare-AI. Ethics and Inf. Technol. 24, 1","author":"Duke A.","year":"2022","unstructured":"Shaul\u00a0A. Duke. 2022. Deny, Dismiss and Downplay: Developers\u2019 Attitudes towards Risk and Their Role in Risk Creation in the Field of Healthcare-AI. Ethics and Inf. Technol. 24, 1 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17828"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Matthew Hutson. 2018. Artificial intelligence faces reproducibility crisis.","DOI":"10.1126\/science.359.6377.725"},{"key":"e_1_3_2_1_13_1","volume-title":"Knowledge base completion: Baselines strike back. arXiv preprint arXiv:1705.10744","author":"Kadlec Rudolf","year":"2017","unstructured":"Rudolf Kadlec, Ondrej Bajgar, and Jan Kleindienst. 2017. Knowledge base completion: Baselines strike back. arXiv preprint arXiv:1705.10744 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Leakage and the reproducibility crisis in ML-based science. arXiv preprint arXiv:2207.07048","author":"Kapoor Sayash","year":"2022","unstructured":"Sayash Kapoor and Arvind Narayanan. 2022. Leakage and the reproducibility crisis in ML-based science. arXiv preprint arXiv:2207.07048 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2382577.2382579"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLHCC.2019.8818850"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3304221.3319751"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TE.2009.2038992"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WAIN52551.2021.00028"},{"key":"e_1_3_2_1_20_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Liao Thomas","year":"2021","unstructured":"Thomas Liao, Rohan Taori, Inioluwa\u00a0Deborah Raji, and Ludwig Schmidt. 2021. Are we learning yet? A meta-review of evaluation failures across machine learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_21_1","volume-title":"How to avoid machine learning pitfalls: a guide for academic researchers. arXiv preprint arXiv:2108.02497","author":"Lones A.","year":"2021","unstructured":"Michael\u00a0A. Lones. 2021. How to avoid machine learning pitfalls: a guide for academic researchers. arXiv preprint arXiv:2108.02497 (2021)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376727"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.05.024"},{"key":"e_1_3_2_1_24_1","volume-title":"Interrater reliability: the kappa statistic. Biochemia medica 22, 3","author":"McHugh L.","year":"2012","unstructured":"Mary\u00a0L. McHugh. 2012. Interrater reliability: the kappa statistic. Biochemia medica 22, 3 (2012), 276\u2013282."},{"volume-title":"Introduction to AI robotics","author":"Murphy R.","key":"e_1_3_2_1_25_1","unstructured":"Robin\u00a0R. Murphy. 2019. Introduction to AI robotics. MIT press."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884790"},{"key":"e_1_3_2_1_27_1","volume-title":"Maggie\u00a0Jiahong Su, Iris Heung\u00a0Yue Yim, Maggie\u00a0Shen Qiao, and Samuel Kai\u00a0Wah Chu.","author":"Tsz\u00a0Kit Ng Davy","year":"2022","unstructured":"Davy Tsz\u00a0Kit Ng, Jac Ka\u00a0Lok Leung, Maggie\u00a0Jiahong Su, Iris Heung\u00a0Yue Yim, Maggie\u00a0Shen Qiao, and Samuel Kai\u00a0Wah Chu. 2022. AI literacy in K-16 classrooms. Springer."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533378"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077618"},{"key":"e_1_3_2_1_30_1","volume-title":"AI in health and medicine. Nature medicine 28, 1","author":"Rajpurkar Pranav","year":"2022","unstructured":"Pranav Rajpurkar, Emma Chen, Oishi Banerjee, and Eric\u00a0J Topol. 2022. AI in health and medicine. Nature medicine 28, 1 (2022), 31\u201338."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2009.193"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-010-9150-8"},{"key":"e_1_3_2_1_33_1","unstructured":"Mehran Sahami Susan Dumais David Heckerman and Eric Horvitz. 1998. A Bayesian approach to filtering junk e-mail. In Learning for Text Categorization: Papers from the 1998 workshop Vol.\u00a062. Citeseer 98\u2013105."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3029387.3029399"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478431.3499397"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287324.3287392"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336124"},{"key":"e_1_3_2_1_38_1","unstructured":"Josh Tobin Sergey Karayev and Pieter Abbeel. 2021. Troubleshooting deep neural networks."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Angelina Wang Sayash Kapoor Solon Barocas Solon Barocas and Arvind Narayanan. 2023. Against Predictive Optimization: On the Legitimacy of Decision-Making Algorithms that Optimize Predictive Accuracy(ACM FAccT \u201923).","DOI":"10.1145\/3593013.3594030"},{"key":"e_1_3_2_1_40_1","volume-title":"Qualitative Analysis of Content. Applications of Social Research Methods to Questions in Information and Library Science (01","author":"Zhang Yan","year":"2009","unstructured":"Yan Zhang and Barbara Wildemuth. 2009. Qualitative Analysis of Content. Applications of Social Research Methods to Questions in Information and Library Science (01 2009)."}],"event":{"name":"Koli Calling '23: 23rd Koli Calling International Conference on Computing Education Research","acronym":"Koli Calling '23","location":"Koli Finland"},"container-title":["Proceedings of the 23rd Koli Calling International Conference on Computing Education Research"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631802.3631808","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3631802.3631808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:18:57Z","timestamp":1755879537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631802.3631808"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":40,"alternative-id":["10.1145\/3631802.3631808","10.1145\/3631802"],"URL":"https:\/\/doi.org\/10.1145\/3631802.3631808","relation":{},"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"2024-02-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}