{
  "fetched_at": "2026-10-19T09:39:04Z",
  "source_url": "https://www.kaggle.com/competitions/guess-the-correlation/data",
  "pages": [
    {
      "name": "rules",
      "content": "\r\n\t<!-- Begin Base Rules -->\r\n    <h3>One account per participant</h3>\r\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n    <h3>No private sharing outside teams</h3>\r\n    <p>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>Team mergers are not allowed in this competition.</p>\r\n\r\n    <h3>Team Limits</h3>\r\n    <p>There is no maximum team size.</p>\r\n    <h3>Submission Limits</h3>\r\n    <p>You may submit a maximum of 2 entries per day.</p>\r\n    <p>You may select up to 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>TBA</strong></p>\r\n    <p>Merger Deadline: <strong>None</strong></p>\r\n    <p>Entry Deadline: <strong>None</strong></p>\r\n    <p>End Date: <strong>2/1/2014 12:00 AM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "## File descriptions\n\n- **train_imgs.zip** - folder with 150.000 png files with size 150x150 pixels to use to train your model.\n- **test_imgs.zip** - folder with 50.000 png files with size 150x150 pixels to use to test your model.\n- **example_submition.csv** - an example of what the layout that we expect you to submit to be evaluated.\n- **train_responses.csv** - the table with the ground truth correlations of each scatterplot of the images of the training set.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "If you don't know the Guess The Correlation Game, [go there](http://guessthecorrelation.com/) and play it for a while.\n\nIf you don't know what (Linear) Correlation is, [go to wiki](https://en.wikipedia.org/wiki/Correlation_coefficient) to have some clue about what it is.\n\nThe goal is: build a function that, given an image containing of a scatterplot, it returns the respective linear correlation coefficient of it. \n\nHave fun!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation). Despite the fact that the response lies between -1 and 1, the RMSE seems to be reasonable and is easy to setup it here in Kaggle. \n\n## Submission Format\nFor every image in the test dataset, you need to associate a number between -1 and 1 corresponding to the corresponding correlation of the plot. \n\nThe file should contain a header and have comma separated values. In other words, it should have the following format:\n\n    id,corr\n    yaeieoky,-0.46898267371580005\n    xaniymhw,-0.2557522007264197\n    vonrkrnq,0.1457067267037928\n    zobcmzde,0.8164155799895525\n    vmfmkfqg,-0.5966361379250884\n    xxjbecwx,0.7967793699353933",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}