{
  "id": 202869,
  "title": "Coming soon shake-up with a public notebook",
  "url": "/competitions/rfcx-species-audio-detection/discussion/202869",
  "author_name": "",
  "post_date": "2020-12-12T11:59:20.942961300Z",
  "votes": null,
  "comment_count": 6,
  "views": 0,
  "content": "<p>Hi<br>\nI hate shakeup on LB but I find the public kernel that has a good potential to do shakeup on LB, after submission I got 0.824 on the leaderboard with overfitting kernel.<br>\nUnfortunately, I can't delete the LB result, working on my own model and I don't want to use it for the final submission and PLEASE don't use this kernel if you find it.<br>\nThank you</p>",
  "messages": [
    {
      "id": "1110072",
      "postDate": "12/12/2020 11:59:20",
      "content": "<p>Hi<br>\nI hate shakeup on LB but I find the public kernel that has a good potential to do shakeup on LB, after submission I got 0.824 on the leaderboard with overfitting kernel.<br>\nUnfortunately, I can't delete the LB result, working on my own model and I don't want to use it for the final submission and PLEASE don't use this kernel if you find it.<br>\nThank you</p>",
      "rawMarkdown": "Hi\nI hate shakeup on LB but I find the public kernel that has a good potential to do shakeup on LB, after submission I got 0.824 on the leaderboard with overfitting kernel.\nUnfortunately, I can't delete the LB result, working on my own model and I don't want to use it for the final submission and PLEASE don't use this kernel if you find it.\nThank you",
      "votes": null
    },
    {
      "id": "1110092",
      "postDate": "12/12/2020 12:20:55",
      "content": "<p>Even if you and other many competitors don't use overfitting notebook, I think this competition has a good potential to make us shaken up.</p>",
      "rawMarkdown": "Even if you and other many competitors don't use overfitting notebook, I think this competition has a good potential to make us shaken up.",
      "votes": null
    },
    {
      "id": "1110116",
      "postDate": "12/12/2020 12:46:58",
      "content": "<p>Yeah, this competition like the birdcall competition can make us shake-up but if don't use this type of kernel we can enjoy this competition. on the other hand, we have to just trust our CV.</p>",
      "rawMarkdown": "Yeah, this competition like the birdcall competition can make us shake-up but if don't use this type of kernel we can enjoy this competition. on the other hand, we have to just trust our CV.",
      "votes": null
    },
    {
      "id": "1110122",
      "postDate": "12/12/2020 12:54:04",
      "content": "<p>Trust CV can be also a bit dangerous because some concerns are expressed on the quality of the annotation.</p>\n<p><a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/202456\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/202456</a><br>\n<a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/201920\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/201920</a></p>",
      "rawMarkdown": "Trust CV can be also a bit dangerous because some concerns are expressed on the quality of the annotation.\n\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/202456\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/201920",
      "votes": null
    },
    {
      "id": "1110130",
      "postDate": "12/12/2020 13:03:18",
      "content": "<p>Got it, Thank you for info.</p>",
      "rawMarkdown": "Got it, Thank you for info.",
      "votes": null
    },
    {
      "id": "1110177",
      "postDate": "12/12/2020 13:48:42",
      "content": "<blockquote>\n  <p>after submission I got 0.824 on the leaderboard with overfitting kernel.</p>\n</blockquote>\n<p>And why exactly do you think that it overfits?</p>\n<blockquote>\n  <p>and PLEASE don't use this kernel if you find it.</p>\n</blockquote>\n<p>You know that no matter what you write here - a day after you will see 20 entires with 0.824 on leaderboard?</p>",
      "rawMarkdown": "> after submission I got 0.824 on the leaderboard with overfitting kernel.\n\nAnd why exactly do you think that it overfits?\n\n> and PLEASE don't use this kernel if you find it.\n\nYou know that no matter what you write here - a day after you will see 20 entires with 0.824 on leaderboard?",
      "votes": null
    },
    {
      "id": "1110220",
      "postDate": "12/12/2020 14:27:11",
      "content": "<p>1: Check the CV<br>\n2: Not exactly 0.824 but I hope ppl read this topic and don't use this kernel.</p>",
      "rawMarkdown": "1: Check the CV\n2: Not exactly 0.824 but I hope ppl read this topic and don't use this kernel.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1110092,
      "author_name": "hidehisaarai1213",
      "author_url": "",
      "post_date": "12/12/2020 12:20:55",
      "content": "<p>Even if you and other many competitors don't use overfitting notebook, I think this competition has a good potential to make us shaken up.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1110116,
          "author_name": "",
          "author_url": "",
          "post_date": "12/12/2020 12:46:58",
          "content": "<p>Yeah, this competition like the birdcall competition can make us shake-up but if don't use this type of kernel we can enjoy this competition. on the other hand, we have to just trust our CV.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1110122,
          "author_name": "hidehisaarai1213",
          "author_url": "",
          "post_date": "12/12/2020 12:54:04",
          "content": "<p>Trust CV can be also a bit dangerous because some concerns are expressed on the quality of the annotation.</p>\n<p><a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/202456\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/202456</a><br>\n<a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/201920\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/201920</a></p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1110130,
          "author_name": "",
          "author_url": "",
          "post_date": "12/12/2020 13:03:18",
          "content": "<p>Got it, Thank you for info.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1110177,
      "author_name": "fffrrt",
      "author_url": "",
      "post_date": "12/12/2020 13:48:42",
      "content": "<blockquote>\n  <p>after submission I got 0.824 on the leaderboard with overfitting kernel.</p>\n</blockquote>\n<p>And why exactly do you think that it overfits?</p>\n<blockquote>\n  <p>and PLEASE don't use this kernel if you find it.</p>\n</blockquote>\n<p>You know that no matter what you write here - a day after you will see 20 entires with 0.824 on leaderboard?</p>",
      "votes": null,
      "replies": [
        {
          "id": 1110220,
          "author_name": "",
          "author_url": "",
          "post_date": "12/12/2020 14:27:11",
          "content": "<p>1: Check the CV<br>\n2: Not exactly 0.824 but I hope ppl read this topic and don't use this kernel.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1110072": "Hi\nI hate shakeup on LB but I find the public kernel that has a good potential to do shakeup on LB, after submission I got 0.824 on the leaderboard with overfitting kernel.\nUnfortunately, I can't delete the LB result, working on my own model and I don't want to use it for the final submission and PLEASE don't use this kernel if you find it.\nThank you",
    "1110092": "Even if you and other many competitors don't use overfitting notebook, I think this competition has a good potential to make us shaken up.",
    "1110116": "Yeah, this competition like the birdcall competition can make us shake-up but if don't use this type of kernel we can enjoy this competition. on the other hand, we have to just trust our CV.",
    "1110122": "Trust CV can be also a bit dangerous because some concerns are expressed on the quality of the annotation.\n\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/202456\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/201920",
    "1110130": "Got it, Thank you for info.",
    "1110177": "> after submission I got 0.824 on the leaderboard with overfitting kernel.\n\nAnd why exactly do you think that it overfits?\n\n> and PLEASE don't use this kernel if you find it.\n\nYou know that no matter what you write here - a day after you will see 20 entires with 0.824 on leaderboard?",
    "1110220": "1: Check the CV\n2: Not exactly 0.824 but I hope ppl read this topic and don't use this kernel."
  },
  "source": "meta"
}