{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:31:33Z","timestamp":1761006693128,"version":"build-2065373602"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T00:00:00Z","timestamp":1760918400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T00:00:00Z","timestamp":1760918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP220101516"],"award-info":[{"award-number":["DP220101516"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Process Sci"],"DOI":"10.1007\/s44311-025-00027-3","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T09:47:36Z","timestamp":1760953656000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalization estimation in process mining: the impact of event data quality"],"prefix":"10.1007","volume":"2","author":[{"given":"Anandi","family":"Karunaratne","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Artem","family":"Polyvyanyy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alistair","family":"Moffat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,20]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","unstructured":"Alkhammash H, Polyvyanyy A, Moffat A et\u00a0al (2020) Discovered process models 2020-08. https:\/\/doi.org\/10.26188\/12814535","DOI":"10.26188\/12814535"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bose RPJC, Mans RS, van der Aalst WMP Wanna improve process mining results? In: IEEE Symposium on Computational Intelligence and Data Mining. IEEE, Singapore. 2013","DOI":"10.1109\/CIDM.2013.6597227"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Buijs JCAM, van Dongen B, van der Aalst WMP Quality dimensions in process discovery: The importance of fitness, precision, generalization and simplicity. International Journal of Cooperative Information Systems. 2014. 23:1440001:1-1440001:39\u00a0","DOI":"10.1142\/S0218843014400012"},{"key":"27_CR4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1890\/13-0133.1","volume":"84","author":"A Chao","year":"2014","unstructured":"Chao A, Gotelli NJ, Hsieh TC (2014) Rarefaction and extrapolation with hill numbers: a framework for sampling and estimation in species diversity studies. Ecological Monographs 84:45\u201367","journal-title":"Ecological Monographs"},{"key":"27_CR5","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.1890\/11-1952.1","volume":"93","author":"A Chao","year":"2012","unstructured":"Chao A, Jost L (2012) Coverage-based rarefaction and extrapolation: standardizing samples by completeness rather than size. Ecology 93:2533\u20132547","journal-title":"Ecology"},{"key":"27_CR6","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1080\/01621459.1992.10475194","volume":"87","author":"A Chao","year":"1992","unstructured":"Chao A, Lee SM (1992) Estimating the number of classes via sample coverage. Journal of the American Statistical Association 87:210\u2013217","journal-title":"Journal of the American Statistical Association"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Colwell RK , Biodiversity: concepts, patterns, and measurement. The Princeton Guide to Ecology. Princeton University Press, New Jersey, 2009. pp 257\u2013263","DOI":"10.1515\/9781400833023.257"},{"key":"27_CR8","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/TKDE.2016.2614680","volume":"29","author":"R Conforti","year":"2016","unstructured":"Conforti R, La Rosa M, ter Hofstede AHM (2016) Filtering out infrequent behavior from business process event logs. IEEE Transactions on Knowledge and Data Engineering 29:300\u2013314","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"27_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/1-84628-168-7","volume-title":"A Modern Introduction to Probability and Statistics","author":"FM Dekking","year":"2005","unstructured":"Dekking FM, Kraaikamp C, Lopuha\u00e4 HP et al (2005) A Modern Introduction to Probability and Statistics. Springer, London"},{"key":"27_CR10","doi-asserted-by":"publisher","DOI":"10.4121\/UUID:270FD440-1057-4FB9-89A9-B699B47990F5","author":"M De Leoni","year":"2015","unstructured":"De Leoni M, Mannhardt F (2015). Road traffic fine management process. https:\/\/doi.org\/10.4121\/UUID:270FD440-1057-4FB9-89A9-B699B47990F5","journal-title":"Road traffic fine management process"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Depaire B, Janssenswillen G, Leemans SJJ, Alpha precision: estimating the significant system behavior in a model. International Conference on Business Process Management. Springer, M\u00fcnster, 2022. pp 120\u2013136","DOI":"10.1007\/978-3-031-16171-1_8"},{"key":"27_CR12","first-page":"1","volume":"14","author":"M Fani Sani","year":"2019","unstructured":"Fani Sani M, van Zelst S, van der Aalst WMP (2019) Repairing outlier behaviour in event logs using contextual behaviour. Enterprise Modelling and and Information Systems Architectures 14:1\u201324","journal-title":"Enterprise Modelling and Information Systems Architectures"},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/s12599-018-0567-8","volume":"61","author":"G Janssenswillen","year":"2018","unstructured":"Janssenswillen G, Depaire B (2018) Towards confirmatory process discovery: making assertions about the underlying system. Bussiness and Information Systems Engineering 61:713\u2013728","journal-title":"Business and Information Systems Engineering"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Kabierski M, Richter M, Weidlich M (2025) Quantifying and relating the completeness and diversity of process representations using species estimation. Information Systems 130:102512:1\u2013102512:23","DOI":"10.1016\/j.is.2024.102512"},{"key":"27_CR15","unstructured":"Karunaratne A, Polyvyanyy A, Moffat A (2024a) Entropia: Measuring log representativeness and generalization of discovered process models. In: Doctoral Consortium and Demo Track at the International Conference on Process Mining. CEUR-WS.org, Lyngby"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Karunaratne A, Polyvyanyy A, Moffat A. The role of log representativeness in estimating generalization in process mining. In: International Conference on Process Mining. IEEE, Lyngby, 2024. pp 33\u201340","DOI":"10.1109\/ICPM63005.2024.10680679"},{"key":"27_CR17","doi-asserted-by":"publisher","first-page":"88","DOI":"10.2307\/2533199","volume":"50","author":"SM Lee","year":"1994","unstructured":"Lee SM, Chao A (1994) Estimating population size via sample coverage for closed capture-recapture models. Biometrics 50:88\u201397","journal-title":"Biometrics"},{"key":"27_CR18","doi-asserted-by":"publisher","unstructured":"Mannhardt F (2016). Sepsis cases - event log. https:\/\/doi.org\/10.4121\/UUID:915D2BFB-7E84-49AD-A286-DC35F063A460","DOI":"10.4121\/UUID:915D2BFB-7E84-49AD-A286-DC35F063A460"},{"key":"27_CR19","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10618-005-0029-z","volume":"13","author":"L M\u0103ru\u015fter","year":"2006","unstructured":"M\u0103ru\u015fter L, Weijters AJMM, van der Aalst WMP et al (2006) A rule-based approach for process discovery: dealing with noise and imbalance in process logs. Data Mining and Knowledge Discovery 13:67\u201387","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"2","key":"27_CR20","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/TSC.2018.2805912","volume":"14","author":"J Pei","year":"2021","unstructured":"Pei J, Wen L, Yang H (2021) Estimating global completeness of event logs: a comparative study. IEEE Transactions on Service Computing 14(2):441\u2013457","journal-title":"IEEE Transactions on Services Computing"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Polyvyanyy A, Moffat A, Garc\u00eda-Ba\u00f1uelos L. An entropic relevance measure for stochastic conformance checking in process mining. In: International Conference on Process Mining. IEEE, Padua, 2020. pp 97\u2013104","DOI":"10.1109\/ICPM49681.2020.00024"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Polyvyanyy A, Moffat A, Garc\u00eda-Ba\u00f1uelos L. Bootstrapping generalization of process models discovered from event data. International Conference on Advanced Information Systems Engineering. Springer, Leuven, 2022. pp 36\u201354","DOI":"10.1007\/978-3-031-07472-1_3"},{"key":"27_CR23","doi-asserted-by":"publisher","first-page":"17:1","DOI":"10.1145\/3387909","volume":"29","author":"A Polyvyanyy","year":"2020","unstructured":"Polyvyanyy A, Solti A, Weidlich M et al (2020) Monotone precision and recall measures for comparing executions and specifications of dynamic systems. ACM Transactions on Software Engineering and Methodology 29:17:1-17:41","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"27_CR24","doi-asserted-by":"publisher","unstructured":"Steeman W (2014) BPI challenge 2013. https:\/\/doi.org\/10.4121\/UUID:A7CE5C55-03A7-4583-B855-98B86E1A2B07","DOI":"10.4121\/UUID:A7CE5C55-03A7-4583-B855-98B86E1A2B07"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Syring AF, Tax N, van der Aalst WMP. Evaluating conformance measures in process mining using conformance propositions. Transactions on Petri Nets and Other Models of Concurrency. 2019:XIV 192\u2013221.","DOI":"10.1007\/978-3-662-60651-3_8"},{"key":"27_CR26","doi-asserted-by":"publisher","first-page":"194410","DOI":"10.1109\/ACCESS.2020.3033450","volume":"8","author":"J Theis","year":"2020","unstructured":"Theis J, Darabi H (2020) Adversarial system variant approximation to quantify process model generalization. IEEE Access 8:194410\u2013194427","journal-title":"IEEE Access"},{"key":"27_CR27","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.2307\/2937956","volume":"106","author":"A Tversky","year":"1991","unstructured":"Tversky A, Kahneman D (1991) Loss aversion in riskless choice: a reference-dependent model. The Quarterly Journal of Economics 106:1039\u20131061","journal-title":"The Quarterly Journal of Economics"},{"key":"27_CR28","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1109\/TKDE.2013.130","volume":"26","author":"SKLM vanden Broucke","year":"2014","unstructured":"vanden Broucke SKLM, DeWeerdt J, Vanthienen J, Baesens B (2014) Determining process model precision and generalization with weighted artificial negative events. IEEE Transactions on Knowledge and Data Engineering 26:1877\u20131889","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"van der Aalst WMP (2016) Process discovery: An introduction. Process Mining. Springer, Berlin, pp 163\u2013194","DOI":"10.1007\/978-3-662-49851-4_6"},{"key":"27_CR30","unstructured":"van\u00a0der\u00a0Aalst WMP (2018) Relating process models and event logs\u201421 conformance propositions. In: Algorithms & Theories for the Analysis of Event Data. CEUR-WS.org, Bratislava, pp 56\u201374"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"van der Aalst WMP, Adriansyah A, van Dongen B (2012) Replaying history on process models for conformance checking and performance analysis. WIREs Data Mining and Knowledge Discovery 2:182\u2013192","DOI":"10.1002\/widm.1045"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"van der Aalst WMP et al (2012) Process mining manifesto. In: Business Process Mining Workshops. Springer, Tallinn, pp 169\u2013194","DOI":"10.1007\/978-3-642-19345-3"},{"key":"27_CR33","first-page":"102155:1","volume":"114","author":"JMEM Werf","year":"2023","unstructured":"Werf JMEM, Polyvyanyy A, Wensveen BR et al (2023) All that glitters is not gold: Four maturity stages of process discovery algorithms. Inf Syst 114:102155:1-102155:12","journal-title":"Inf Syst"},{"key":"27_CR34","doi-asserted-by":"publisher","unstructured":"van\u00a0Dongen B (2012) BPI challenge 2012. https:\/\/doi.org\/10.4121\/UUID:3926DB30-F712-4394-AEBC-75976070E91F","DOI":"10.4121\/UUID:3926DB30-F712-4394-AEBC-75976070E91F"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"van Dongen B, Carmona J, Chatain T. A unified approach for measuring precision and generalization based on anti-alignments. International Conference on Business Process Management. Springer, Rio de Janeiro, 2016. pp 39\u201356.","DOI":"10.1007\/978-3-319-45348-4_3"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"van Hee KM, Liu Z, Sidorova N. Is my event log complete? - a probabilistic approach to process mining. In: International Conference on Research Challenges in Information Science. IEEE, Gosier, 2011. pp 1\u201312.","DOI":"10.1109\/RCIS.2011.6006848"},{"key":"27_CR37","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1080\/15275920590913868","volume":"6","author":"J Warren","year":"2005","unstructured":"Warren J (2005) Representativeness of environmental samples. Environmental Forensics 6:21\u201325","journal-title":"Environmental Forensics"},{"key":"27_CR38","unstructured":"Yang H, ter Hofstede AHM, van Dongen B et al. On global completeness of event logs. BPM Center Report BPM-10-09. 2010."},{"key":"27_CR39","unstructured":"Yang H, van Dongen B, ter Hofstede AHM et\u00a0al (2012a) Estimating completeness of event logs. BPM Center Report BPM-12-03"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Yang H, Wen L, Wang J (2012) An approach to evaluate the local completeness of an event log. In: International Conference on Data Mining. IEEE, Brussels, pp 1164\u20131169","DOI":"10.1109\/ICDM.2012.66"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Yang H, Wen L, Wang J et al (2014) CPL+: an improved approach for evaluating the local completeness of event logs. Information Processing Letters 114:607\u2013610","DOI":"10.1016\/j.ipl.2014.06.001"}],"container-title":["Process Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44311-025-00027-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44311-025-00027-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44311-025-00027-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T09:47:48Z","timestamp":1760953668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44311-025-00027-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,20]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["27"],"URL":"https:\/\/doi.org\/10.1007\/s44311-025-00027-3","relation":{},"ISSN":["2948-2178"],"issn-type":[{"value":"2948-2178","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,20]]},"assertion":[{"value":"12 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 October 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"20"}}