Strozzii/MazeMind

AI Summary: Statistically prove the correlation between the MazeMind model's Cyber Risk Score (CRS) and the likelihood of a real-world attack using historical attack data. This involves applying the model to historical data and performing statistical analysis to demonstrate a significant correlation between a higher CRS and a higher probability of a successful attack.

AI Summary: Create a pipeline to collect, clean, and prepare historical vulnerability scan data and corresponding breach labels ('was_breached') for model validation in a machine learning project focused on cyber risk scoring using logistic regression.

AI Summary: Create a placeholder function, `calculate_cwss`, within the `src/theseus/cwe_scoring.py` file. This function should initially return the CWSS score directly from the `CweFinding` object, acting as a temporary stand-in for a more sophisticated calculation to be implemented later. This prepares the codebase for future enhancements to the CWSS scoring mechanism.

AI Summary: Create Python dataclasses to represent vulnerability data used in a machine learning model for cyber risk scoring. This involves defining the structure and attributes of the data to be used for training and prediction within the MazeMind project.