Supplemental Material to the SWJ Journal Submission "Characteristic Sets Profile Feature: Estimation and Application to SPARQL Query Planning"

Large Files and subdirectories are zipped. Raw data includes tab-separated files (.tsv) and JSON (.json) files. ## Files - `statistical_similarity_measures_per_sample`: Statistical Similarity Measures aggregated on the level of Samples. - `structural_similarity_measures_per_sample`: Structural Similarity Measures aggregated on the level of Samples. - `fedbench_datasets_statistics`: General Statistics of the datasets from FedBench used in the experiments. - `characteristic_sets_all_samples`: All individual characteristic sets obtained from the samples. - `fedbench_results_complete`: All evaluation metrics for all FedBench Queries per CSPF from each sample.

Aggregated similarity measures are included as well. - `cspf_statistics`: Directory containing all estimated (and complete) CSPF estimations used by the Query Planner