[
  {
    "MSE (10% missing)": 0.334,
    "code_links": [],
    "date": "2019-08-10",
    "date2": 20190810,
    "model": "E^2GAN",
    "paper": {
      "title": "E2GAN: End-to-End Generative Adversarial Network or Multivariate Time Series Imputation",
      "url": "https://cknow.io/lib/d6816e2584024971"
    },
    "paper_data_uoa": "d6816e2584024971"
  },
  {
    "MSE (10% missing)": 0.355,
    "code_links": [],
    "date": "2018-12-01",
    "date2": 20181201,
    "model": "GAN-2-stage",
    "paper": {
      "title": "Multivariate Time Series Imputation with Generative Adversarial Networks",
      "url": "https://cknow.io/lib/efdf4f9b873d6d1c"
    },
    "paper_data_uoa": "efdf4f9b873d6d1c"
  },
  {
    "MSE (10% missing)": 0.378,
    "code_links": [
      {
        "title": "jsyoon0823/GAIN",
        "url": "https://github.com/jsyoon0823/GAIN"
      },
      {
        "title": "CKPOON0619/GAIN",
        "url": "https://github.com/CKPOON0619/GAIN"
      },
      {
        "title": "dhanajitb/GAIN-Pytorch",
        "url": "https://github.com/dhanajitb/GAIN-Pytorch"
      }
    ],
    "date": "2018-06-07",
    "date2": 20180607,
    "model": "GAIN",
    "paper": {
      "title": "GAIN: Missing Data Imputation using Generative Adversarial Nets",
      "url": "https://cknow.io/lib/a098a78ae47642be"
    },
    "paper_data_uoa": "a098a78ae47642be"
  },
  {
    "MSE (10% missing)": 0.468,
    "code_links": [
      {
        "title": "stefvanbuuren/mice",
        "url": "https://github.com/stefvanbuuren/mice"
      }
    ],
    "date": "2010-11-30",
    "date2": 20101130,
    "model": "MICE",
    "paper": {
      "title": "Multiple imputation using chained equations: issues and guidance for practice",
      "url": "https://cknow.io/lib/4f97d54e769e5d6f"
    },
    "paper_data_uoa": "4f97d54e769e5d6f"
  }
]