Hello,

I have a question regarding the format of the report that will be provided during the inference for this task. After reading the papers referenced by the organizers, I noticed some differences in how the report is used. For example, in the "GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes" paper, the report is used as a text prompt in the format: {age} years old {sex}: {impression}.

On the other hand, the "Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography" paper uses a combination of findings + impression as the report input. Given these differences, could you clarify what kind of report format will be provided at inference time? - Will metadata such as age and sex also be included? - Will the report consist of specific sections such as Technique_EN, Impression_EN, ClinicalInformation_EN, or Finding_EN, or a subset of these?

Or are these papers merely provided for reference, and one of the goals of this challenge is to develop models that can handle flexible, free‑form report formats and still generate the corresponding CT volumes accurately?

Thank you in advance!