Supplemental material for: Software System Testing assisted by Large Language Models: An Exploratory Study

This is the supplemental material of the paper titled as “Software System Testing Assisted by Large Language Models: An Exploratory Study” presented at the 36th International Conference on Testing Software and Systems.

It contains the raw execution data generated by both models, GPT-4o and GPT-4omini, during the exploratory study. The supplementary material includes the following files:

GPT-4ominiRQ1-2ExecutionData.zip: contains the JSON outputs from the OpenAI API for the GPT-4o mini model. Each output is labeled according to the research question number and the corresponding timestamp (for RQ1) or the requested test case (for RQ2), all provided in plain text format.

GPT-4oRQ1-2ExecutionData.zip: contains the JSON outputs from the OpenAI API for the GPT-4o model. Like the previous file, each output is named in plain text format based on the research question number and timestamp (for RQ1) or the requested test case (for RQ2).

To cite this work: 

C. Augusto, J. Morán, A. Bertolino, C. de la Riva and J. Tuya, “Software System Testing assisted by Large Language Models: An Exploratory Study”, in 36th International Conference on Testing Software and Systems, London (England), XXXX, November 2024, doi: XXXXX