{
  "id": 542161,
  "title": "Benchmark scoring lower than on the leaderboard",
  "url": "/competitions/applications-of-deep-learning-wustl-fall-2024/discussion/542161",
  "author_name": "",
  "post_date": "2024-10-23T08:32:51.762359300Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I submitted the benchmark just as a test, but the benchmark is actually getting a lower score than the supposed score on the leaderboard. Is it because of new data added?</p>",
  "messages": [
    {
      "id": "3025889",
      "postDate": "10/23/2024 08:32:51",
      "content": "<p>I submitted the benchmark just as a test, but the benchmark is actually getting a lower score than the supposed score on the leaderboard. Is it because of new data added?</p>",
      "rawMarkdown": "I submitted the benchmark just as a test, but the benchmark is actually getting a lower score than the supposed score on the leaderboard. Is it because of new data added?",
      "votes": null
    },
    {
      "id": "3030812",
      "postDate": "10/28/2024 23:14:51",
      "content": "<p>I believe the minor differences are resulting from randomness in the cross-validation or grid search, as the benchmark is performing similar to the two other submissions that have been made so far. No new data will be added.</p>",
      "rawMarkdown": "I believe the minor differences are resulting from randomness in the cross-validation or grid search, as the benchmark is performing similar to the two other submissions that have been made so far. No new data will be added.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3030812,
      "author_name": "robertjirsaraie",
      "author_url": "",
      "post_date": "10/28/2024 23:14:51",
      "content": "<p>I believe the minor differences are resulting from randomness in the cross-validation or grid search, as the benchmark is performing similar to the two other submissions that have been made so far. No new data will be added.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "3025889": "I submitted the benchmark just as a test, but the benchmark is actually getting a lower score than the supposed score on the leaderboard. Is it because of new data added?",
    "3030812": "I believe the minor differences are resulting from randomness in the cross-validation or grid search, as the benchmark is performing similar to the two other submissions that have been made so far. No new data will be added."
  },
  "source": "meta"
}