Submissions to the DRAGON benchmark should be open-source and accompanied by a method description. The open-source submission may be kept private temporarily to facilitate e.g. manuscript submissions.

Open Source Policy for Training Resources¶

Submissions to the DRAGON challenge should become available to all researchers such that the whole research field moves forward. To achieve this, all submissions should become open source and should be accompanied by a document detailing the used methodology. Open source in this context means that all resources are accessible to the public and that other scientists can exactly replicate the method.

In practice, this means that the submission should be based on a GitHub repository with a permissive license (e.g., CC-BY-NC-SA 4.0, see e.g. choosealicense.com for more information on open source licenses). To verify all resources are included in this repository, please build the algorithm container by linking this repository to Grand Challenge.

In case you want to make the code public later, please see below.

Method Description¶

Prepare a document (in PDF format; minimum 1 page; no restrictions on template or maximum length), briefly covering the model design and training strategy of your AI algorithm. Please include the names, designations and contact details of your team members in this document. You can upload this document using the "Supplementary File" field in the submission form. If you're submitting an AI algorithm that has already been presented in one of your team's prior publications, then you can directly share a URL to that publication. Please note, this step is mandatory. 

In case you don't want the method description to be public just yet, you can send the PDF to joeran.bosma@radboudumc.nl. The description can then be added at a later date, see below for the rules.

Delayed Published Training Resources and/or Methods Descriptions¶

To address potential conflicts with academic processes, such as the submission of papers to journals, submissions are not required to be open source immediately. A grace period of up to six months is permitted, with potential extensions available upon justified request (for example, if the manuscript is still under review). These requirements are designed to ensure that high-performing contributions are shared with the broader research community in a timely manner.

After the grace period ends, the resources may be made publicly available by the challenge organizers, if they are not made public yet by the challenge participants.