# DLMMDD Workshop: Synthetic Image Attribution — Data

来源：https://www.kaggle.com/competitions/dlmmdd-workshop-synthetic-source-attribution-challenge/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Participants will be provided with a dataset released exclusively for this challenge. The dataset
itself is composed of 10 open-source text-to-image models (all available on Hugging Face1).
In particular, it is obtained by taking the prompt list of the WILD dataset 2, and using the
prompts to generate new images with the sources. The dataset includes:
• a labeled training set;
• an unlabeled test set → ground-truth labels of the test set will remain private.
The dataset may not be redistributed or used outside the scope of this challenge.

## Files

*   **sources.txt** - file that matches the source class number to the actual generator
*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

*   `ID` - image ID
*   `path` - file path to the image 
*   `y` - supervision
*   `TARGET` - prediction