{
  "fetched_at": "2026-10-24T15:47:43Z",
  "source_url": "https://www.kaggle.com/competitions/202410-hy-12143-artifical-intelligence/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **test** - image folder for testset images\n*   **test.csv** - the test set\n*   **submission.csv** - the submission file\n\n## Labels\n0 = fake face\n1 = real face",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "You can find a link to the RFP here:\nhttps://drive.google.com/file/d/1Ot2dT7EmHNE-wScdW0YKfHRx0C7HbBjj/view?usp=sharing\n\nDo remember to check the LMS for any announcements\nYou can email me for further inquiries or leave a comment at the discussion forum",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [area under the ROC curve](http://en.wikipedia.org/wiki/Receiver_operating_characteristic) between the predicted probability and the observed target.\n\n\n## Submission File\nYou will be given a submission.csv, each Image in the test set, you must predict a probability for the Label variable. The file should contain a header and have the following format:\n\n    Image,Label\n    \"00000.jpg\",0\n    \"00001.jpg\",0\n    \"00002.jpg\",1\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "A reminder based on the RFP and also Q&A from discussions:\n- The solutions proposed for this project should be runnable/trainable on Google Colab\n- You can use any method you'd like to implement\n- You can use a pre-trained model\n- You must implement your method from scratch and not use a pre-defined function that essentially does the project for you",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Here you will be provided with the test set folder of images alongside a submissions.csv, your job is to fill in the submissions.csv with the following labels:\n0 = fake faces\n1 = real faces",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}