{
  "id": 34762,
  "title": "Given stg1 test label, still need predict stg1 test? confused",
  "url": "/competitions/intel-mobileodt-cervical-cancer-screening/discussion/34762",
  "author_name": "",
  "post_date": "2017-06-15T10:49:53.292018500Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I'm confused about stage2 submission rules <strong>from data</strong> below:</p>\n\n<ul>\n<li>sample_submission_stg2.csv - a sample submission file in the correct format for stage 2. Please note that you still need to predict the test set from the 1st stage, which is 0.jpg to 511.jpg.Updated June 15,2017.</li>\n<li>solution_stg1_release.csv - stage 1 test data labels release. Updated June 15,2017.</li>\n</ul>\n\n<p>Given stage1 test label, submission still need to contain stage1 test set? strange!</p>",
  "messages": [
    {
      "id": "193007",
      "postDate": "06/15/2017 10:49:53",
      "content": "<p>I'm confused about stage2 submission rules <strong>from data</strong> below:</p>\n\n<ul>\n<li>sample_submission_stg2.csv - a sample submission file in the correct format for stage 2. Please note that you still need to predict the test set from the 1st stage, which is 0.jpg to 511.jpg.Updated June 15,2017.</li>\n<li>solution_stg1_release.csv - stage 1 test data labels release. Updated June 15,2017.</li>\n</ul>\n\n<p>Given stage1 test label, submission still need to contain stage1 test set? strange!</p>",
      "rawMarkdown": "I'm confused about stage2 submission rules **from data** below:\n\n*  sample_submission_stg2.csv - a sample submission file in the correct format for stage 2. Please note that you still need to predict the test set from the 1st stage, which is 0.jpg to 511.jpg.Updated June 15,2017.\n*  solution_stg1_release.csv - stage 1 test data labels release. Updated June 15,2017.\n\nGiven stage1 test label, submission still need to contain stage1 test set? strange!",
      "votes": null
    },
    {
      "id": "193026",
      "postDate": "06/15/2017 11:59:56",
      "content": "<p>@Wendy: This way the leaderboard is not reflective of the model in addition to creating this confusion. Instead of revealing the test_stg1 labels, Kaggle could try increasing the precision of the logloss scores that are displayed on a competition based on the total submissions possible over the competition period to prevent LB mining? That way the stg1 labels wouldn't need to be revealed and still would be fair to the competitors. </p>",
      "rawMarkdown": "Wendy: This way the leaderboard is not reflective of the model in addition to creating this confusion. Instead of revealing the test_stg1 labels, Kaggle could try increasing the precision of the logloss scores that are displayed on a competition based on the total submissions possible over the competition period to prevent LB mining? That way the stg1 labels wouldn't need to be revealed and still would be fair to the competitors.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 193026,
      "author_name": "bvineeth007",
      "author_url": "",
      "post_date": "06/15/2017 11:59:56",
      "content": "<p>@Wendy: This way the leaderboard is not reflective of the model in addition to creating this confusion. Instead of revealing the test_stg1 labels, Kaggle could try increasing the precision of the logloss scores that are displayed on a competition based on the total submissions possible over the competition period to prevent LB mining? That way the stg1 labels wouldn't need to be revealed and still would be fair to the competitors. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "193007": "I'm confused about stage2 submission rules **from data** below:\n\n*  sample_submission_stg2.csv - a sample submission file in the correct format for stage 2. Please note that you still need to predict the test set from the 1st stage, which is 0.jpg to 511.jpg.Updated June 15,2017.\n*  solution_stg1_release.csv - stage 1 test data labels release. Updated June 15,2017.\n\nGiven stage1 test label, submission still need to contain stage1 test set? strange!",
    "193026": "Wendy: This way the leaderboard is not reflective of the model in addition to creating this confusion. Instead of revealing the test_stg1 labels, Kaggle could try increasing the precision of the logloss scores that are displayed on a competition based on the total submissions possible over the competition period to prevent LB mining? That way the stg1 labels wouldn't need to be revealed and still would be fair to the competitors."
  },
  "source": "meta"
}