{
  "fetched_at": "2026-10-25T05:09:29Z",
  "source_url": "https://www.kaggle.com/competitions/11-785-winter-2019-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": "# Dataset\nThe dataset is available at www.kaggle.com/dataset/8a99a96b764d822da11ce50c9ce9d7a69f5064989c4347b382d3217e7897c2f9 and the sample submission is attached below.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Face Verification\n\nAn 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.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric is the [AUC score](https://www.kaggle.com/learn-forum/53782).\n\n# Submission Format\n\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
    }
  ]
}