{
  "fetched_at": "2026-10-19T13:06:32Z",
  "source_url": "https://www.kaggle.com/competitions/dlai-8-digit-recognizer/data",
  "pages": [
    {
      "name": "data-description",
      "content": "***The following description is based on the Digit Recognizer competition by Kaggle.***  *The training data set is the same as the one from Digit Recognizer.*  *However, it is likely there are a few out-of-distribution data and possibly some data leakage in the test set.*\n\nThe data files train.csv and test.csv contain gray-scale images of hand-drawn digits, from zero through nine.\n\nEach image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0 and 255, inclusive.\n\nThe training data set, (train.csv), has 785 columns. The first column, called \"label\", is the digit that was drawn by the user. The rest of the columns contain the pixel-values of the associated image.\n\nEach pixel column in the training set has a name like pixelx, where x is an integer between 0 and 783, inclusive. To locate this pixel on the image, suppose that we have decomposed x as x = i * 28 + j, where i and j are integers between 0 and 27, inclusive. Then pixelx is located on row i and column j of a 28 x 28 matrix, (indexing by zero).\n\nFor example, pixel31 indicates the pixel that is in the fourth column from the left, and the second row from the top, as in the ascii-diagram below.\n\nVisually, if we omit the \"pixel\" prefix, the pixels make up the image like this:\n\n> 000 001 002 003 ... 026 027\n>\n> 028 029 030 031 ... 054 055\n>\n> 056 057 058 059 ... 082 083\n>\n> ...\n>\n> 728 729 730 731 ... 754 755\n>\n> 756 757 758 759 ... 782 783 \n\nThe test data set, (test.csv), does not contain the \"label\" column.\n\nYour submission file should be in the following format: For each of the images in the test set, output a single line containing the ImageId and the digit you predict. For example, if you predict that the first image is of a 3, the second image is of a 7, and the third image is of a 8, then your submission file would look like:\n\n> ImageId,Label\n>\n> 1,3\n>\n> 2,7\n>\n> 3,8 \n>\n> (... more lines)\n\n\nThe evaluation metric for this contest is the categorization accuracy, or the proportion of test images that are correctly classified. For example, a categorization accuracy of 0.97 indicates that you have correctly classified all but 3% of the images.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "***This is based on Kaggle's Digit Recognizer competition at [https://www.kaggle.com/competitions/digit-recognizer/overview](https://www.kaggle.com/competitions/digit-recognizer/overview). The labels of the test set from the Digit Recognizer competition are available widely and may be used by some as part of the training set, leading to perfect accuracy scores which skews the actual performance of the prediction models. This competition uses a near leakage-free test set that would provide a better assessment of the model performance on the Leaderboard. The initial test data set (source to be disclosed) likely contains out-of-distribution samples that shows potential biases in the MNIST data set. Updated test data set may be used before the end of the competition.***\n\nThe following is taken from the Kaggle competition description with minor changes.\n\n### Competition Description\n\nMNIST (\"Modified National Institute of Standards and Technology\") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.\n\nIn this competition, your goal is to correctly identify digits from a dataset of tens of thousands of handwritten images. We’ve curated a set of tutorial-style kernels which cover everything from regression to neural networks. We encourage you to experiment with different algorithms to learn first-hand what works well and how techniques compare.\nPractice Skills\n\n-     Computer vision fundamentals including simple neural networks\n-     Classification methods such as SVM and K-nearest neighbors\n\n### Acknowledgements \n\nMore details about the dataset, including algorithms that have been tried on it and their levels of success, can be found at [http://yann.lecun.com/exdb/mnist/index.html](http://yann.lecun.com/exdb/mnist/index.html). The dataset is made available under a [Creative Commons Attribution-Share Alike 3.0 license](https://creativecommons.org/licenses/by-sa/3.0/).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "### Goal\n\nThe goal in this competition is to take an image of a handwritten single digit, and determine what that digit is.\nFor every in the test set, you should predict the correct label.\n\n### Metric\n\nThis competition is evaluated on the macro f-score.\n\n### Submission File Format\n\nThe file should contain a header and have the following format:\n\n> ImageId,Label\n1,0\n2,0\n3,0\netc. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "### One account per participant\n\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n### No private sharing outside teams\n\nPrivately sharing code or data is not permitted. It's okay to share code if made available to all participants on the forums.\n\n### Submission Limits\n\nYou may submit a maximum of 15 entries per day.\n\nYou may select up to 2 final submissions for judging.\n\n### Competition Timeline\n\nStart Date: July16, 2024 (UTC time)\nEnd Date: July 20, 2024 (UTC time) ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}