Replication Data for: Identifying latent workforce capacities for extreme heat resilience: An artificial intelligence assisted approach

This dataset supports the findings of the paper “Identifying Latent Workforce Capacities for Extreme Heat Solutions in Arizona Using Large Language Models,” and provides a structured assessment of how occupational tasks and work contexts in Arizona relate to solving challenges posed by extreme heat. The data were developed using the O*NET occupational task database and publicly available employment statistics from the Bureau of Labor Statistics (BLS). Using GPT-4, a large language model (LLM), we evaluated each occupational task for its relevance to solving extreme heat challenges across seven predefined roles (e.g., public service, engineering, environmental adaptation). The dataset also includes occupation-level aggregations and contextual information related to heat exposure.