{
  "fetched_at": "2026-10-19T06:25:12Z",
  "source_url": "https://www.kaggle.com/competitions/events-detection/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Files `train.csv` and `sample_submission.csv` contain `label` and `fname`  as columns.\n\n`fname` is filename, and `train.csv` describes the files in `audio_train` folder, while `sample_submission.csv`contains all the names from the test set. \n\nTo make a submission you should change zeroes in `sample_submission.csv` to meaningful class names as in `train.csv`.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "### Data analysis competition of the course \"Acoustic Events Detection\".\n\n### Baseline: https://github.com/Tvicker/itmo-kaggle-inclass\n\nYou will get 'passed' grade when you beat the baseline.\n\nYour solutions will be scored with average class-based [ F1-score ](https://en.wikipedia.org/wiki/F1_score).\n\nPublic Leaderboard contains 30% of all the data. This means that your score on public leaderboard fo not show the full picture and your solution will be rescored after competition ends.\n\nPlease, ensure to set the seed when you do any randomness in your notebook. These lines of code must help:\n\n```\nimport random\nimport numpy as np\n\nrandom.seed(42)\nnp.random.seed(42)\ntorch.manual_seed(42)\ntorch.cuda.manual_seed(42)\ntorch.backends.cudnn.deterministic = True\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:</p>\n<hr>\n<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The 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.</p>\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids.&nbsp;For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>AuthorId,DuplicateAuthorIds<br>1,1<br></pre>",
      "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 - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}