{
  "fetched_at": "2026-10-19T08:06:29Z",
  "source_url": "https://www.kaggle.com/competitions/gnr-650-assignment-1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Each csv has pixel color information as columns. Training CSV contains corresponding ground truth labels.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "N/A",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation section describes how submissions will be scored and how participants should format their submissions. You don't need a sub-title at the top; the page title appears above. Below is an example of a typical evaluation page.\n\n---\n\nSubmissions are evaluated on accuracy between the predicted class and ground truth class.\n\n\n## Submission File\nFor each ID in the test set, you must predict a class for the TARGET variable. The file should contain a header and have the following format:\n\n    ID,TARGET\n    2,0\n    5,0\n    6,0\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This assignment is designed to tackle the problem of image classification in the presence of noisy labels, a common issue in real-world datasets where the labels may be incorrectly assigned due to human error, automated labeling processes, or inherent ambiguities in the data. \n\nThe objective of this assignment is to perform image classification on the CIFAR-100 dataset, where 40% of the labels have been deliberately corrupted randomly. The goal is to evaluate the robustness and performance of the Vision Transformer (ViT) model in the presence of noisy labels.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}