{
  "fetched_at": "2026-10-24T03:04:16Z",
  "source_url": "https://www.kaggle.com/competitions/bioverse-hackathon-f/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n* All training images are found in the \"train\" folder and they are organized into 3 folders for each class. The images are also saved in folders that signify patient ID.\n*  All test images are found in the \"test\" folder. These are the images you will run the model on for predictions for your submissions.\n*  sample_submission.csv - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The F1 score can be interpreted as a harmonic mean of the precision and recall, where an F1 score reaches its best value at 1 and worst score at 0.\n\nThe relative contribution of precision and recall to the F1 score are equal. The formula for the F1 score is:\n\n$$F1 = 2 * (precision * recall) / (precision + recall)$$",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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 - The score shown on the Kaggle leaderboard during the competition is only the public score which is calculated on around 66% of the data. The private score is revealed at the end of the competition. Please have this in mind!\n - The evaluation metric is Fscore\n - No submissions are allowed outside the Kaggle competition\n - Each team will have 6 submissions total on Kaggle and one notebook\n - The Kaggle competition will end at 8:30PM sharp. No submissions will be allowed after that.\n - Please use your full team name in your Kaggle submissions and refrain from using made-up names, just to help us track who is submitting! (This can be done by setting the \"Kaggle team name\", make sure that all 2-3 members are invited on the team as well)\n - By the end of the competition, contestants should submit their coding notebook into the competition as it will contribute to the total score which will be calculated as a combination of Notebook Readability, Kaggle Score, and Inference Time (which should be already calculated in the submitted notebook, if it is not present, the contestant will recieve a 0 in Inference Time).\n - Please make sure to fully reference any code you use from other sources. Plagiarism can cost you a penalty on your score\n - The readability rubric can be found below. Kaggle score and inference times are calculated based on the leaderboards and on the highest inference time among contestants. \n - The final score is an aggregation of the three scores!\n \n|Category   |Metric                                       |\n|-----------|---------------------------------------------|\n|Data Exploration|Significant Data Exploration Findings        |\n|           |Good Visualizations                          |\n|Use of Markdown|Good titles and sectioning                   |\n|           |Meaningful comments                          |\n|           |Clear explanation of thought process         |\n|           |Clear explanation of model components        |\n|           |Emojis (Bonus)                               |\n|Training Statistics (Printed during training)|Loss                                         |\n|           |Validation accuracy                          |\n|Plotting   |Learning curve                               |\n|           |Comparison of model learning curves (bonus)  |\n|Coherence  |No unused cells or commented cells           |\n|           |Logical flow of cells (no need to scroll up to check old values)|\n|           |No repeated cells                            |\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the BioVerse Hackathon!\n\nIn this hackathon, use your skills in Machine Learning and Deep Learning to classify if breast tumors are beneign, malignant, or the lack of a tumor in the first place!\n\nThis is real data provided by Baheya.\n\nThe competition also includes an extra challenge. The amount of data is very small. Use your knowledge and research about few-shot learning to try to get the highest score possible!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}