{
  "fetched_at": "2026-10-24T08:15:00Z",
  "source_url": "https://www.kaggle.com/competitions/cu-dl-spring-2019-hw2/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "TODO: Add data description here. Do we need to update data files below to not include test set? ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>The data files for the competition are disjoint training and test sets. \"train.csv\" corresponds to the training data with 4 fields needed to effectively train your model to map from \"input\" to \"expected.\" \"test.csv\" contains all the same fields as \"train.csv\" but without the expected field. It is your job to output the expected field corresponding to each \"id\" and upload that as a submission. </p>\n\n<h2>File descriptions </h2>\n* input.txt \n    *  TODO: describe the inputs below. \n* output_angles.txt\n* output_angle.npz\n* output_distances.txt\n* output_dist_mat.npz\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>When you submit solutions, you will create a CSV with two columns: ID and Predicted. Since your output will be distance matrices, we will create n^2 points for every n x n distance matrix. In other words, for every distance matrix, make new points where the ID is {casp_id}_{i}_{j} for points i, j = 0,...,n - 1, and the Predicted is the (i, j) element of the predicted distance matrix for that protein. </p>\n<hr />\n<p>The evaluation metric for this competition is the root mean squared error across these distance matrix values. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}