{
  "id": 253619,
  "title": "Most TP/FP and TN/FN",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/253619",
  "author_name": "",
  "post_date": "2021-07-17T13:42:32.474937300Z",
  "votes": 2,
  "comment_count": 5,
  "views": 0,
  "content": "<p>Maybe the top &gt;.874 can share some top TP/FP and TN/FN to the rest of us cretins so we can reassure our plebeian models?</p>\n<p>This ![<a href=\"https://photos.app.goo.gl/3iyFBc2za1J7Tros6\" target=\"_blank\">https://photos.app.goo.gl/3iyFBc2za1J7Tros6</a>] is my spectrogram of 00000e74ad. I do not see any \"chirp\"</p>",
  "messages": [
    {
      "id": "1391317",
      "postDate": "07/17/2021 13:42:32",
      "content": "<p>Maybe the top &gt;.874 can share some top TP/FP and TN/FN to the rest of us cretins so we can reassure our plebeian models?</p>\n<p>This ![<a href=\"https://photos.app.goo.gl/3iyFBc2za1J7Tros6\" target=\"_blank\">https://photos.app.goo.gl/3iyFBc2za1J7Tros6</a>] is my spectrogram of 00000e74ad. I do not see any \"chirp\"</p>",
      "rawMarkdown": "Maybe the top >.874 can share some top TP/FP and TN/FN to the rest of us cretins so we can reassure our plebeian models?\n\nThis ![https://photos.app.goo.gl/3iyFBc2za1J7Tros6] is my spectrogram of 00000e74ad. I do not see any \"chirp\"",
      "votes": null
    },
    {
      "id": "1391616",
      "postDate": "07/17/2021 19:17:23",
      "content": "<p>Nice try ;)</p>\n<p>You have not submitted yet unless mistaken.  Submitting would give you some feedback on how good is your method.  Nothing says you are  a cretin, and I doubt you are one.</p>\n<p>To your point I can't see anything in the data and I relay on my model for that.</p>",
      "rawMarkdown": "Nice try ;)\n\nYou have not submitted yet unless mistaken.  Submitting would give you some feedback on how good is your method.  Nothing says you are  a cretin, and I doubt you are one.\n\nTo your point I can't see anything in the data and I relay on my model for that.",
      "votes": null
    },
    {
      "id": "1391650",
      "postDate": "07/17/2021 20:34:52",
      "content": "<p>If you or your model could \"see\" every positive example, then top score would be 1.000 instead of 0.878. Some of the generated signals have such low SNR that their detection are not expected.</p>",
      "rawMarkdown": "If you or your model could \"see\" every positive example, then top score would be 1.000 instead of 0.878. Some of the generated signals have such low SNR that their detection are not expected.",
      "votes": null
    },
    {
      "id": "1392454",
      "postDate": "07/18/2021 17:44:46",
      "content": "<p>Yes, food for thought, indeed. I was hopeful there were some easy chirps. Not much of a reveal to say \"Id x was signalest\". But, I get your point. Exaplainable ML is bothering me, and it should not. Like I posted elsewhere: I have no submissions because I have no original idea…</p>",
      "rawMarkdown": "Yes, food for thought, indeed. I was hopeful there were some easy chirps. Not much of a reveal to say \"Id x was signalest\". But, I get your point. Exaplainable ML is bothering me, and it should not. Like I posted elsewhere: I have no submissions because I have no original idea...",
      "votes": null
    },
    {
      "id": "1393179",
      "postDate": "07/19/2021 12:48:40",
      "content": "<p>Just in case anybody wants to check their preprocessing on an extreme example: id 098a464da9 is an extremely strong signal, easily visible by eye and therefore not at all typical.<br>\n<img src=\"https://i.imgur.com/Rr9lOId.png\" alt=\"Plot\"></p>",
      "rawMarkdown": "Just in case anybody wants to check their preprocessing on an extreme example: id 098a464da9 is an extremely strong signal, easily visible by eye and therefore not at all typical.\n![Plot](https://i.imgur.com/Rr9lOId.png)",
      "votes": null
    },
    {
      "id": "1561272",
      "postDate": "10/27/2021 13:11:28",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "rawMarkdown": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1391616,
      "author_name": "cpmpml",
      "author_url": "",
      "post_date": "07/17/2021 19:17:23",
      "content": "<p>Nice try ;)</p>\n<p>You have not submitted yet unless mistaken.  Submitting would give you some feedback on how good is your method.  Nothing says you are  a cretin, and I doubt you are one.</p>\n<p>To your point I can't see anything in the data and I relay on my model for that.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1392454,
          "author_name": "glimmung",
          "author_url": "",
          "post_date": "07/18/2021 17:44:46",
          "content": "<p>Yes, food for thought, indeed. I was hopeful there were some easy chirps. Not much of a reveal to say \"Id x was signalest\". But, I get your point. Exaplainable ML is bothering me, and it should not. Like I posted elsewhere: I have no submissions because I have no original idea…</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1391650,
      "author_name": "fffrrt",
      "author_url": "",
      "post_date": "07/17/2021 20:34:52",
      "content": "<p>If you or your model could \"see\" every positive example, then top score would be 1.000 instead of 0.878. Some of the generated signals have such low SNR that their detection are not expected.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1393179,
      "author_name": "friedchips",
      "author_url": "",
      "post_date": "07/19/2021 12:48:40",
      "content": "<p>Just in case anybody wants to check their preprocessing on an extreme example: id 098a464da9 is an extremely strong signal, easily visible by eye and therefore not at all typical.<br>\n<img src=\"https://i.imgur.com/Rr9lOId.png\" alt=\"Plot\"></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1561272,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/27/2021 13:11:28",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1391317": "Maybe the top >.874 can share some top TP/FP and TN/FN to the rest of us cretins so we can reassure our plebeian models?\n\nThis ![https://photos.app.goo.gl/3iyFBc2za1J7Tros6] is my spectrogram of 00000e74ad. I do not see any \"chirp\"",
    "1391616": "Nice try ;)\n\nYou have not submitted yet unless mistaken.  Submitting would give you some feedback on how good is your method.  Nothing says you are  a cretin, and I doubt you are one.\n\nTo your point I can't see anything in the data and I relay on my model for that.",
    "1391650": "If you or your model could \"see\" every positive example, then top score would be 1.000 instead of 0.878. Some of the generated signals have such low SNR that their detection are not expected.",
    "1392454": "Yes, food for thought, indeed. I was hopeful there were some easy chirps. Not much of a reveal to say \"Id x was signalest\". But, I get your point. Exaplainable ML is bothering me, and it should not. Like I posted elsewhere: I have no submissions because I have no original idea...",
    "1393179": "Just in case anybody wants to check their preprocessing on an extreme example: id 098a464da9 is an extremely strong signal, easily visible by eye and therefore not at all typical.\n![Plot](https://i.imgur.com/Rr9lOId.png)",
    "1561272": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris"
  },
  "source": "meta"
}