Dataset comprising 608 samples of the specific heat capacity at constant pressure (Cp) of carbon dioxide

To model the specific heat capacity at constant pressure (Cp) of carbon dioxide using machine learning algorithms, a dataset comprising 608 samples and three key variables—namely pressure, temperature, and Cp—was extracted and compiled from reputable sources and previously published studies. In constructing this database, particular attention was given to the experimental measurement challenges near the critical point; a systematic review of the literature indicates that direct quantification of this property in that region is experimentally intractable. To address this gap, approximately 8.22% of the total data were generated through extrapolation based on reliable experimental data, thereby compensating for the lack of direct measurements and ensuring a complete dataset suitable for training and evaluating machine learning models.