{
  "id": 576050,
  "title": "Problem of test data",
  "url": "/competitions/animal-clef-2025/discussion/576050",
  "author_name": "",
  "post_date": "2025-05-02T11:58:12.542005300Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello, It is said that \"This leaderboard is calculated with approximately 31% of the test data. The final results will be based on the other 69%, so the final standings may be different.\"  That means the result is calculated by using (total row numbers*0.31) samples in submission.csv, Isn't it?</p>",
  "messages": [
    {
      "id": "3192038",
      "postDate": "05/02/2025 11:58:12",
      "content": "<p>Hello, It is said that \"This leaderboard is calculated with approximately 31% of the test data. The final results will be based on the other 69%, so the final standings may be different.\"  That means the result is calculated by using (total row numbers*0.31) samples in submission.csv, Isn't it?</p>",
      "rawMarkdown": "Hello, It is said that \"This leaderboard is calculated with approximately 31% of the test data. The final results will be based on the other 69%, so the final standings may be different.\"  That means the result is calculated by using (total row numbers*0.31) samples in submission.csv, Isn't it?",
      "votes": null
    },
    {
      "id": "3192058",
      "postDate": "05/02/2025 12:24:24",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/hathawaytan\" target=\"_blank\">@hathawaytan</a> ,</p>\n<p>Kaggle calculates performance on the 31% and 69% separately. There is nothing like \"<em>total row numbers*0.31</em>\".<br>\nHowever, the final standing my change since different data are used for evaluation.</p>\n<p>Best,<br>\nLukas</p>",
      "rawMarkdown": "Hi @hathawaytan ,\n\nKaggle calculates performance on the 31% and 69% separately. There is nothing like \"_total row numbers*0.31_\".\nHowever, the final standing my change since different data are used for evaluation.\n\nBest,\nLukas",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3192058,
      "author_name": "picekl",
      "author_url": "",
      "post_date": "05/02/2025 12:24:24",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/hathawaytan\" target=\"_blank\">@hathawaytan</a> ,</p>\n<p>Kaggle calculates performance on the 31% and 69% separately. There is nothing like \"<em>total row numbers*0.31</em>\".<br>\nHowever, the final standing my change since different data are used for evaluation.</p>\n<p>Best,<br>\nLukas</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "3192038": "Hello, It is said that \"This leaderboard is calculated with approximately 31% of the test data. The final results will be based on the other 69%, so the final standings may be different.\"  That means the result is calculated by using (total row numbers*0.31) samples in submission.csv, Isn't it?",
    "3192058": "Hi @hathawaytan ,\n\nKaggle calculates performance on the 31% and 69% separately. There is nothing like \"_total row numbers*0.31_\".\nHowever, the final standing my change since different data are used for evaluation.\n\nBest,\nLukas"
  },
  "source": "meta"
}