{
  "fetched_at": "2026-10-19T07:34:27Z",
  "source_url": "https://www.kaggle.com/competitions/11785-f19-hw2p2-verification/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>You can download the data below. </p>\n\n\n<p>As mentioned in the part 2 handout, the <code>score.py</code> utility is:</p>\n<pre><code>from sklearn.metrics import roc_auc_score\nimport sys\nimport pandas as pd\n\ndef get_auc(y_true, y_score):\n    auc = roc_auc_score(y_true, y_score)\n    return auc\n\nif __name__ == '__main__':\n    args = sys.argv[1:]\n    if len(args) < 2:\n        print \"python score.py <score_csv> <label_csv>\"\n        exit()\n    score_csv = args[0]\n    label_csv = args[1]\n    y_score = pd.read_csv(score_csv).score.values\n    y_true = pd.read_csv(label_csv).score.values\n    auc = get_auc(y_true, y_score)\n    print \"AUC: \", auc</code></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1>Face Verification</h1>\n<p> An input to your system is a trial, that is, a pair of face images that may or may not belong to the same person. Given a trial, your goal is to output a numeric score that quantifies how similar the images of the two people appear to be. On some scale, a higher score will indicate higher confidence that the two images belong to one and the same person in fact. </p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/learn-forum/53782\"> AUC score.</a> </p>\n<h1> Submission Format </h1>\nYou will submit a csv file created form the trials_test provided to you. The first column will be the same as the one in the trials_test and the second column will be the similarity score you compute.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}