{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:39:58Z","timestamp":1757623198931,"version":"3.44.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032042064","type":"print"},{"value":"9783032042071","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04207-1_21","type":"book-chapter","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T03:32:05Z","timestamp":1757388725000},"page":"317-326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Ground Truth Effect: Investigating SZZ Variants in\u00a0Just-in-Time Vulnerability Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0209-5974","authenticated-orcid":false,"given":"Alfonso","family":"Cannavale","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7489-9969","authenticated-orcid":false,"given":"Emanuele","family":"Iannone","sequence":"additional","affiliation":[]},{"given":"Gianluca","family":"Di Lillo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9337-5116","authenticated-orcid":false,"given":"Fabio","family":"Palomba","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-1425","authenticated-orcid":false,"given":"Andrea","family":"De Lucia","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"21_CR1","unstructured":"Ralph, P., et al.: Empirical standards for software engineering research (2021)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Bao, L., Xia, X., Hassan, A.E., Yang, X.: V-SZZ: automatic identification of version ranges affected by CVE vulnerabilities. In: Proceedings of the 44th International Conference on Software Engineering, pp. 2352\u20132364 (2022)","DOI":"10.1145\/3510003.3510113"},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45, 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Routledge (2017)","DOI":"10.1201\/9781315139470"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Cannavale, A., Iannone, E., Di Lillo, G., Palomba, F., De Lucia, A.: The ground truth effect: dataset and materials (supplementary) (2025). https:\/\/doi.org\/10.6084\/m9.figshare.28788857","DOI":"10.6084\/m9.figshare.28788857"},{"key":"21_CR6","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"issue":"6","key":"21_CR7","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/32.295895","volume":"20","author":"SR Chidamber","year":"1994","unstructured":"Chidamber, S.R., Kemerer, C.F.: A metrics suite for object oriented design. IEEE Trans. Software Eng. 20(6), 476\u2013493 (1994)","journal-title":"IEEE Trans. Software Eng."},{"issue":"7","key":"21_CR8","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/TSE.2016.2616306","volume":"43","author":"DA Da Costa","year":"2016","unstructured":"Da Costa, D.A., McIntosh, S., Shang, W., Kulesza, U., Coelho, R., Hassan, A.E.: A framework for evaluating the results of the SZZ approach for identifying bug-introducing changes. IEEE Trans. Software Eng. 43(7), 641\u2013657 (2016)","journal-title":"IEEE Trans. Software Eng."},{"issue":"1","key":"21_CR9","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1002\/smr.1619","volume":"26","author":"S Davies","year":"2014","unstructured":"Davies, S., Roper, M., Wood, M.: Comparing text-based and dependence-based approaches for determining the origins of bugs. J. Softw. Evol. Process 26(1), 107\u2013139 (2014)","journal-title":"J. Softw. Evol. Process"},{"key":"21_CR10","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(Jan), 1\u201330 (2006)"},{"issue":"8","key":"21_CR11","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1109\/TSE.2019.2929761","volume":"47","author":"Y Fan","year":"2019","unstructured":"Fan, Y., Xia, X., Da Costa, D.A., Lo, D., Hassan, A.E., Li, S.: The impact of mislabeled changes by SZZ on just-in-time defect prediction. IEEE Trans. Software Eng. 47(8), 1559\u20131586 (2019)","journal-title":"IEEE Trans. Software Eng."},{"key":"21_CR12","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez, A., Garcia, S., Herrera, F., Chawla, N.V.: Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863\u2013905 (2018)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"21_CR13","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119\u2013139 (1997)","journal-title":"J. Comput. Syst. Sci."},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 1189\u20131232 (2001)","DOI":"10.1214\/aos\/1013203451"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63, 3\u201342 (2006)","journal-title":"Mach. Learn."},{"issue":"1","key":"21_CR16","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TSE.2022.3140868","volume":"49","author":"E Iannone","year":"2022","unstructured":"Iannone, E., Guadagni, R., Ferrucci, F., De Lucia, A., Palomba, F.: The secret life of software vulnerabilities: a large-scale empirical study. IEEE Trans. Software Eng. 49(1), 44\u201363 (2022)","journal-title":"IEEE Trans. Software Eng."},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S., Zimmermann, T., Pan, K., James\u00a0Jr, E., et\u00a0al.: Automatic identification of bug-introducing changes. In: 21st IEEE\/ACM International Conference on Automated Software Engineering (ASE 2006), pp. 81\u201390. IEEE (2006)","DOI":"10.1109\/ASE.2006.23"},{"issue":"185","key":"21_CR18","first-page":"1","volume":"18","author":"L Li","year":"2018","unstructured":"Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., Talwalkar, A.: Hyperband: a novel bandit-based approach to hyperparameter optimization. J. Mach. Learn. Res. 18(185), 1\u201352 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111283","volume":"188","author":"F Lomio","year":"2022","unstructured":"Lomio, F., Iannone, E., De Lucia, A., Palomba, F., Lenarduzzi, V.: Just-in-time software vulnerability detection: are we there yet? J. Syst. Softw. 188, 111283 (2022)","journal-title":"J. Syst. Softw."},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Morrison, P., Herzig, K., Murphy, B., Williams, L.: Challenges with applying vulnerability prediction models. In: Proceedings of the 2015 Symposium and Bootcamp on the Science of Security, pp.\u00a01\u20139 (2015)","DOI":"10.1145\/2746194.2746198"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Neto, E.C., Da\u00a0Costa, D.A., Kulesza, U.: The impact of refactoring changes on the SZZ algorithm: an empirical study. In: 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 380\u2013390. IEEE (2018)","DOI":"10.1109\/SANER.2018.8330225"},{"key":"21_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2024.112014","volume":"214","author":"S Nguyen","year":"2024","unstructured":"Nguyen, S., Nguyen, T.T., Vu, T.T., Do, T.D., Ngo, K.T., Vo, H.D.: Code-centric learning-based just-in-time vulnerability detection. J. Syst. Softw. 214, 112014 (2024)","journal-title":"J. Syst. Softw."},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"O\u2019brien, R.M.: A caution regarding rules of thumb for variance inflation factors. Qual. Quant. 41, 673\u2013690 (2007)","DOI":"10.1007\/s11135-006-9018-6"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Perl, H., et al.: Vccfinder: finding potential vulnerabilities in open-source projects to assist code audits. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 426\u2013437 (2015)","DOI":"10.1145\/2810103.2813604"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Rajaraman, A., Ullman, J.D.: Mining of Massive Datasets. Cambridge University Press (2011)","DOI":"10.1017\/CBO9781139058452"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Rosa, G., et al.: Evaluating SZZ implementations through a developer-informed oracle. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE), pp. 436\u2013447. IEEE (2021)","DOI":"10.1109\/ICSE43902.2021.00049"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Shin, Y., Williams, L.: An empirical model to predict security vulnerabilities using code complexity metrics. In: Proceedings of the Second ACM-IEEE International Symposium on Empirical Software Engineering and Measurement, pp. 315\u2013317 (2008)","DOI":"10.1145\/1414004.1414065"},{"issue":"4","key":"21_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1082983.1083147","volume":"30","author":"J \u015aliwerski","year":"2005","unstructured":"\u015aliwerski, J., Zimmermann, T., Zeller, A.: When do changes induce fixes? ACM Sigsoft Softw. Eng. Notes 30(4), 1\u20135 (2005)","journal-title":"ACM Sigsoft Softw. Eng. Notes"},{"key":"21_CR29","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","volume":"20","author":"V Vapnik","year":"1995","unstructured":"Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Woolson, R.F.: Wilcoxon signed-rank test. In: Encyclopedia of Biostatistics, vol. 8 (2005)","DOI":"10.1002\/0470011815.b2a15177"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Z.: Introduction to machine learning: k-nearest neighbors. Ann. Transl. Med. 4(11) (2016)","DOI":"10.21037\/atm.2016.03.37"},{"key":"21_CR32","doi-asserted-by":"publisher","unstructured":"Zimmermann, T., Nagappan, N., Williams, L.: Searching for a needle in a haystack: predicting security vulnerabilities for windows vista. In: 2010 Third International Conference on Software Testing, Verification and Validation, pp. 421\u2013428 (2010). https:\/\/doi.org\/10.1109\/ICST.2010.32","DOI":"10.1109\/ICST.2010.32"}],"container-title":["Lecture Notes in Computer Science","Software Engineering and Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04207-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T03:32:20Z","timestamp":1757388740000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04207-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"ISBN":["9783032042064","9783032042071"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04207-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"assertion":[{"value":"9 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SEAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Euromicro Conference on Software Engineering and Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salerno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"51","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"seaa-12025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dsd-seaa.com\/seaa2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}