{
  "id": 439094,
  "title": "CV - LB calibration",
  "url": "/competitions/stanford-ribonanza-rna-folding/discussion/439094",
  "author_name": "",
  "post_date": "2023-09-13T17:04:46.901798800Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Are there any special implementations to the MAE?<br>\nI have CV-LB</p>\n<table>\n<thead>\n<tr>\n<th>LB</th>\n<th>CV</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>.34</td>\n<td>.332</td>\n</tr>\n<tr>\n<td>.238</td>\n<td>.325</td>\n</tr>\n<tr>\n<td>.223</td>\n<td>.32</td>\n</tr>\n<tr>\n<td>.219</td>\n<td>.312</td>\n</tr>\n</tbody>\n</table>\n<p>The null hypothesis seems to agree somewhat. Is the MAE split into two sums, then averaged?<br>\nAny hints? Are the reactivity also clamped to [0,1] ?<br>\n<strong>Edit</strong>: if the clamp is on the difference, it sort of makes sense…</p>",
  "messages": [
    {
      "id": "2436615",
      "postDate": "09/13/2023 17:04:46",
      "content": "<p>Are there any special implementations to the MAE?<br>\nI have CV-LB</p>\n<table>\n<thead>\n<tr>\n<th>LB</th>\n<th>CV</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>.34</td>\n<td>.332</td>\n</tr>\n<tr>\n<td>.238</td>\n<td>.325</td>\n</tr>\n<tr>\n<td>.223</td>\n<td>.32</td>\n</tr>\n<tr>\n<td>.219</td>\n<td>.312</td>\n</tr>\n</tbody>\n</table>\n<p>The null hypothesis seems to agree somewhat. Is the MAE split into two sums, then averaged?<br>\nAny hints? Are the reactivity also clamped to [0,1] ?<br>\n<strong>Edit</strong>: if the clamp is on the difference, it sort of makes sense…</p>",
      "rawMarkdown": "Are there any special implementations to the MAE?\nI have CV-LB\n| LB |CV  |\n| --- | --- |\n| .34 |.332  |\n| .238 |.325  |\n| .223 |.32  |\n| .219 |.312  |\n\nThe null hypothesis seems to agree somewhat. Is the MAE split into two sums, then averaged?\nAny hints? Are the reactivity also clamped to [0,1] ?\n**Edit**: if the clamp is on the difference, it sort of makes sense...",
      "votes": null
    },
    {
      "id": "2436956",
      "postDate": "09/13/2023 23:02:23",
      "content": "<p>It's just simple MAE, nothing special. And yes reactivity values are clamped to [0,1] </p>",
      "rawMarkdown": "It's just simple MAE, nothing special. And yes reactivity values are clamped to [0,1]",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2436956,
      "author_name": "shujun717",
      "author_url": "",
      "post_date": "09/13/2023 23:02:23",
      "content": "<p>It's just simple MAE, nothing special. And yes reactivity values are clamped to [0,1] </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2436615": "Are there any special implementations to the MAE?\nI have CV-LB\n| LB |CV  |\n| --- | --- |\n| .34 |.332  |\n| .238 |.325  |\n| .223 |.32  |\n| .219 |.312  |\n\nThe null hypothesis seems to agree somewhat. Is the MAE split into two sums, then averaged?\nAny hints? Are the reactivity also clamped to [0,1] ?\n**Edit**: if the clamp is on the difference, it sort of makes sense...",
    "2436956": "It's just simple MAE, nothing special. And yes reactivity values are clamped to [0,1]"
  },
  "source": "meta"
}