The field of procedural content generation and generative art is moving towards a more nuanced understanding of the role of uncertainty and randomness in creative processes. Recent research has highlighted the importance of analyzing and quantifying the entropy of generated content, such as game paths and levels, to better understand player behavior and decision-making. Moreover, the development of new tools and frameworks, such as generative art libraries and constrained expressive range analysis, is enabling the creation of more diverse and interesting content. Machine learning models are also being applied to analyze and understand artistic style, including musical style, and to distinguish between human-generated and AI-generated art. Notable papers in this area include:

• Samila: A Generative Art Generator, which introduces a Python-based generative art library that employs mathematical functions and randomness to create visually compelling compositions.
• Deconstructing Jazz Piano Style Using Machine Learning, which trains supervised-learning models to identify iconic jazz musicians and analyzes their decision-making processes.
• Detecting AI-generated Artwork, which considers the potential utility of various types of machine learning models in distinguishing AI-generated artwork from human-generated artwork.