{
  "fetched_at": "2026-10-19T07:40:32Z",
  "source_url": "https://www.kaggle.com/competitions/datarush-2023/data",
  "pages": [
    {
      "name": "data-description",
      "content": "**Files**\n- **train.csv :** the training set\n- **test.csv:**  the test set\n- **sample_submission.csv:**  a sample submission file in the correct format\n\n**Columns**\n- id:  Id\n- title: title of paper\n- abstract: abstract of paper \n- category: Label",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "ArXiv is a public service repository and open-source archive for scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics.\nIn this data challenge, you are given a dataset that contains abstracts and categories columns that are collected from the arXiv portal. There are altogether 157 subject categories. For this competition, you have been provided with dataset having 23 classes. You will have to classify the data into those classes.\n\n**Your task is to build a model to predict the category given paper abstract and title.**\n\nNote that the provided dataset is very imbalanced posing a different challenge and providing a great opportunity to flex your NLP muscles and solve an exciting problem!\nPlease refer to [this file ]\n(https://drive.google.com/file/d/1u8J2hLaNE3cckJmEOM1oEsD11MfC1555/view?usp=share_link)\nto check the distribution of classes.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision ( \\text{p} ) and recall ( \\text{r} ).\n\nPrecision is the ratio of true positives (\\text{tp}) to all predicted positives (\\text{tp} + \\text{fp}). Recall is the ratio of true positives (\\text{tp}) to all actual positives (\\text{tp} + \\text{fn}). The F1 score is given by:\n\n[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} ]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n**Submission Format**\nFor every author in the dataset, submission files should contain two columns: ID and Category.\n\nThe file should contain a header and have the following format:\n\n```\nid, category\n1, cs-CV\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "All the participants will abide by the rules aforementioned.\n\n- A team can have a maximum of 2 members.\n- One account per team is provided for submission in the platform as a\ncredential.\n- Each team has to submit the prediction or data insights on the designated\nplatform.\n- The submission after the deadline will be discarded.\n- Source code and model with proper documentation have to be submitted to\nthe organizing committee for cross-verifying the prediction.\n- Winners should submit the model at the end, so they will be responsible for\nstoring the model with the best performance.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}