Concept Tree Learner (CTL): Synthetic Dataset and Source Code (applsci-4366794)

This record provides the synthetic datasets and the full source code supporting the manuscript "Concept Tree Learner (CTL): An Incremental and Interpretable Symbolic Framework for Binary String Rule Induction" by Muhammed Tekin Ertekin and Burkay Genç, submitted to Applied Sciences (Manuscript ID: applsci-4366794).Each of the 29 example_N.txt files defines one concept-learning task, with one labelled example per line: a binary string followed by + (member of the concept) or − (non-member).ctl-zenodo-v2.zip adds the complete implementation used to produce every table and figure in the paper — the CTL learner, the experiment drivers, the decision-tree and RIPPER baselines, the depth-sweep and ablation studies, and the set-cover robustness check — together with a README stating the environment and the exact commands needed to reproduce the results.Version 2 supersedes version 1, which contained the datasets only.