{
  "id": 6632,
  "title": "release relevance judgements on test file after challenge?",
  "url": "/competitions/yandex-personalized-web-search-challenge/discussion/6632",
  "author_name": "",
  "post_date": "2013-12-19T10:17:43.050Z",
  "votes": null,
  "comment_count": 2,
  "views": 2121,
  "content": "<p>Hi,</p>\n<p>Will you release the true relevance judgements of the URLs in the test data? This could be very helpful for our future research works on related topics using your dataset to evaluate our algorithms.</p>\n<p>&nbsp;</p>\n<p>Thanks a lot.</p>",
  "messages": [
    {
      "id": "36362",
      "postDate": "12/19/2013 10:17:43",
      "content": "<p>Hi,</p>\n<p>Will you release the true relevance judgements of the URLs in the test data? This could be very helpful for our future research works on related topics using your dataset to evaluate our algorithms.</p>\n<p>&nbsp;</p>\n<p>Thanks a lot.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "36413",
      "postDate": "12/20/2013 16:33:11",
      "content": "<p>This is yet to be discussed.</p>\n<p>In any case, 90% (27 days) of the dataset is available and you can split it in test/train subsets and use in your future research.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "38440",
      "postDate": "02/06/2014 17:25:23",
      "content": "<p>Any news about that?<br><br>I am currently trying to reimplement the NDCG computation done by the Kaggle platform on the baseline, using relevances based on what is provided <a href=\"http://www.kaggle.com/c/yandex-personalized-web-search-challenge/details/evaluation\">on Evaluation page</a> but I do not get the exact same results.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 36413,
      "author_name": "eugene1751",
      "author_url": "",
      "post_date": "12/20/2013 16:33:11",
      "content": "<p>This is yet to be discussed.</p>\n<p>In any case, 90% (27 days) of the dataset is available and you can split it in test/train subsets and use in your future research.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 38440,
      "author_name": "theo3153466",
      "author_url": "",
      "post_date": "02/06/2014 17:25:23",
      "content": "<p>Any news about that?<br><br>I am currently trying to reimplement the NDCG computation done by the Kaggle platform on the baseline, using relevances based on what is provided <a href=\"http://www.kaggle.com/c/yandex-personalized-web-search-challenge/details/evaluation\">on Evaluation page</a> but I do not get the exact same results.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "36362": "",
    "36413": "",
    "38440": ""
  },
  "source": "meta"
}