{
  "fetched_at": "2026-10-19T15:50:52Z",
  "source_url": "https://www.kaggle.com/competitions/applications-of-deep-learningwustl-fall-2019/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": "<p>This page shows up underneath the data files. Here you describe what files you have provided and the format of each. There is no single format for this page that is appropriate for all competitons, but you should strive to describe as much as you can here. A little time spent describing the data here can save a lot of time answering questions later.</p>\n<p>Participants should be able to answer questions like these after reading the data description: What files do I need? What should I expect the data format to be? What am I predicting? What acroynms will I encounter?</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sample.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This Kaggle is a project from the course [T81-855: Applications of Deep Learning at Washington University in St. Louis](https://sites.wustl.edu/jeffheaton/t81-558/). All students must create a Kaggle account and submit a solution. If you are a student, once you have submitted your solution entry log into Canvas (at WUSTL) and submit a single file telling me your Kaggle name on the leaderboard (you do not need to register to Kaggle with your real name). This competition will be visible to the public, so there may be non-student submissions as well as from the students.\n\nFor this competition, you will classify if two sentences are from the same source.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"http://wiki.fast.ai/index.php/Log_Loss\">Log Loss</a>. The log loss score, commonly used in binary classification, measures performance of the predicted probability given by a model. The log loss score is given by:</p>\n<p>\\[ -{(y\\log(p) + (1 - y)\\log(1 - p))} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids.&nbsp;For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>id,same_source\n129157,0.5\n129158,0.5\n129159,0.5\n129160,0.5\n129161,0.5\n129162,0.5\n...</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}