Dear editors of Neurosymbolic Artificial Intelligence, This is "Special Issue on NeSy 2025" The extended version of the NeSy 2025 paper “Neurosymbolic Models Based on Hybrids of Convolutional Neural Networks and Decision Trees” is approximately 50–70 % longer than the original. It provides an expanded Related Work section and a more comprehensive description of the optimization algorithm (pages 6–9). In addition, we introduce several new experiments, including analyses of the regularization path (Figure 5), trees with varying sparsity distributions (Figures 4 and 6), tree of receptive field density maps (Figure 8), as well as more detailed explanations and discussions of the experimental results. Best regards, Rasul