Correlation Analysis of TLRA with Species-Discovery Coverage (Ground Truth and Estimation) and Log-System Recall: A Comparative Evaluation Dataset

This dataset supports the study of correlations between <b>Trace-based Log Representativeness Approximation (TLRA)</b> and three measures: species-discovery-based coverage (both estimated and ground truth) and log-system recall. The analysis was conducted across event logs of 60 generative systems and varying log sizes and noise levels.<b>Version 1</b>: Focuses on the correlation analysis between TLRA and species-discovery-based coverage estimation (as presented in ieeexplore.ieee.org/document/10680679).<b>Version 2</b>: Extends the analysis by incorporating log-system recall.<b>Version 3: </b>Includes a ground truth analysis using sample coverage.The systems and logs used for this analysis are available for download in our GitHub repository.We kindly request that you cite our work if you use this dataset in your research:<br><i>A. Karunaratne, A. Polyvyanyy, and A. Moffat, “The role of log representativeness in estimating </i><i>generalization in process mining,” in Int. Conf. Process Mining. IEEE, 2024, pp. 33-40.</i>