{
  "id": 106127,
  "title": "Will the final scores show performance by type?",
  "url": "/competitions/champs-scalar-coupling/discussion/106127",
  "author_name": "",
  "post_date": "2019-08-28T09:58:59.746791700Z",
  "votes": 23,
  "comment_count": 4,
  "views": 0,
  "content": "<p>With the current top scores so close (0.001 between 1st and 2nd!) I was wondering, can the organisers show us the performance of models by coupling type after the deadline? They are already calculated for every submission, so it shouldn't be hard to extract them for a handful of competitors - perhaps for the golds only.</p>\n\n<p>It would be very interesting to see which models and approaches were best at predicting the different types.</p>",
  "messages": [
    {
      "id": "609993",
      "postDate": "08/28/2019 09:58:59",
      "content": "<p>With the current top scores so close (0.001 between 1st and 2nd!) I was wondering, can the organisers show us the performance of models by coupling type after the deadline? They are already calculated for every submission, so it shouldn't be hard to extract them for a handful of competitors - perhaps for the golds only.</p>\n\n<p>It would be very interesting to see which models and approaches were best at predicting the different types.</p>",
      "rawMarkdown": "With the current top scores so close (0.001 between 1st and 2nd!) I was wondering, can the organisers show us the performance of models by coupling type after the deadline? They are already calculated for every submission, so it shouldn't be hard to extract them for a handful of competitors - perhaps for the golds only.\n\nIt would be very interesting to see which models and approaches were best at predicting the different types.",
      "votes": null
    },
    {
      "id": "610075",
      "postDate": "08/28/2019 11:44:28",
      "content": "<p>Can try to do 👍 </p>",
      "rawMarkdown": "Can try to do 👍",
      "votes": null
    },
    {
      "id": "610091",
      "postDate": "08/28/2019 12:10:59",
      "content": "<p>Thank you!</p>",
      "rawMarkdown": "Thank you!",
      "votes": null
    },
    {
      "id": "610544",
      "postDate": "08/28/2019 21:18:33",
      "content": "<p>Glad you asked, this would be really interesting given the different response to the models!</p>",
      "rawMarkdown": "Glad you asked, this would be really interesting given the different response to the models!",
      "votes": null
    },
    {
      "id": "618948",
      "postDate": "09/05/2019 17:16:04",
      "content": "<p>This is now available <a href=\"https://www.kaggle.com/c/champs-scalar-coupling/discussion/107661\">here</a></p>",
      "rawMarkdown": "This is now available [here](https://www.kaggle.com/c/champs-scalar-coupling/discussion/107661)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 610075,
      "author_name": "larsbratholm",
      "author_url": "",
      "post_date": "08/28/2019 11:44:28",
      "content": "<p>Can try to do 👍 </p>",
      "votes": null,
      "replies": [
        {
          "id": 610091,
          "author_name": "bigironsphere",
          "author_url": "",
          "post_date": "08/28/2019 12:10:59",
          "content": "<p>Thank you!</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 618948,
          "author_name": "larsbratholm",
          "author_url": "",
          "post_date": "09/05/2019 17:16:04",
          "content": "<p>This is now available <a href=\"https://www.kaggle.com/c/champs-scalar-coupling/discussion/107661\">here</a></p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 610544,
      "author_name": "asauve",
      "author_url": "",
      "post_date": "08/28/2019 21:18:33",
      "content": "<p>Glad you asked, this would be really interesting given the different response to the models!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "609993": "With the current top scores so close (0.001 between 1st and 2nd!) I was wondering, can the organisers show us the performance of models by coupling type after the deadline? They are already calculated for every submission, so it shouldn't be hard to extract them for a handful of competitors - perhaps for the golds only.\n\nIt would be very interesting to see which models and approaches were best at predicting the different types.",
    "610075": "Can try to do 👍",
    "610091": "Thank you!",
    "610544": "Glad you asked, this would be really interesting given the different response to the models!",
    "618948": "This is now available [here](https://www.kaggle.com/c/champs-scalar-coupling/discussion/107661)"
  },
  "source": "meta"
}