Submissions are evaluated on **Area Under the ROC Curve (AUC)** for each of the 14 thoracic conditions. Your **overall score** is the mean AUC across all conditions. This is a **multi-label classification task**, where each image can have multiple positive labels.

### Submission File Format

Submissions should follow the provided CSV format (example posted below). If you hit any snags, feel free to ask here — we’ll figure it out together:

Image_name,Atelectasis,Cardiomegaly,Consolidation,Edema,Enlarged Cardiomediastinum,Fracture,Lung Lesion,Lung Opacity,No Finding,Pleural Effusion,Pleural Other,Pneumonia,Pneumothorax,Support Devices

Example row:

00000005_001_001.jpg,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1

- Each label should be a probability between 0 and 1.
- The `Image_name` column must exactly match the filenames in the test set.