{
  "@type": "dcat:Dataset",
  "accessLevel": "public",
  "bureauCode": [
    "006:55"
  ],
  "contactPoint": {
    "fn": "Debra Audus",
    "hasEmail": "mailto:debra.audus@nist.gov"
  },
  "description": "A code repository and accompanying data for incorporating imperfect theory into machine learning for improved prediction and explainability. Specifically, it focuses on the case study of the dimensions of a polymer chain in different solvent qualities. Jupyter Notebooks for quickly testing concepts and reproducing figures, as well as source code that computes the mean squared error as a function of dataset size for various machine learning models are included.\n\nFor additional details on the data, please refer to the README.md associated with the data. For additional details on the code, please refer to the README.md provided with the code repository (GitHub Repo for Theory aware Machine Learning). For additional details on the methodology, see Debra J. Audus, Austin McDannald, and Brian DeCost, \"Leveraging Theory for Enhanced Machine Learning\"  *ACS Macro Letters* **2022** *11* (9), 1117-1122 DOI: [10.1021/acsmacrolett.2c00369](https://doi.org/10.1021/acsmacrolett.2c00369).",
  "distribution": [
    {
      "accessURL": "https://github.com/usnistgov/TaML",
      "format": "HTML",
      "title": "GitHub Repo for Theory aware Machine Learning (TaML)"
    },
    {
      "description": "README file for Theory aware Machine Learning (TaML)",
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/README.md",
      "format": "text",
      "mediaType": "text/plain",
      "title": "README"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/README.md.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_difference.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_difference.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_direct.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_direct.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_fixedprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_fixedprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_latentvariable.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_latentvariable.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_linearprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_linearprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_difference.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_difference.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_direct.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_direct.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_fixedprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_fixedprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_latentvariable.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_latentvariable.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_linearprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_linearprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_parameterization.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_parameterization.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_quotient.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_quotient.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_parameterization.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_parameterization.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_quotient.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_quotient.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_difference.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_difference.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_direct.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_direct.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_fixedprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_fixedprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_latentvariable.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_latentvariable.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_linearprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_linearprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_difference.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_difference.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_direct.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_direct.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_fixedprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_fixedprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_latentvariable.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_latentvariable.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_linearprior.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_linearprior.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_parameterization.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_parameterization.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_quotient.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_quotient.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_parameterization.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_parameterization.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_quotient.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_quotient.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/out_theory.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/out_theory.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_difference_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_difference_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_direct_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_direct_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_latentvariable_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_latentvariable_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_multitask_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_multitask_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_difference_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_difference_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_direct_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_direct_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_latentvariable_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_latentvariable_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_multitask_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_multitask_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_quotient_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_quotient_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_quotient_1000_None.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_quotient_1000_None.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/theory.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/theory.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgmaindata.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgmaindata.csv.sha256",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgoutlierdata.csv",
      "mediaType": "text/csv"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgoutlierdata.csv.sha256",
      "mediaType": "text/plain"
    }
  ],
  "identifier": "ark:/88434/mds2-2637",
  "keyword": [
    "machine learning",
    "polymers",
    "theory",
    "transfer learning"
  ],
  "landingPage": "https://data.nist.gov/od/id/mds2-2637",
  "language": [
    "en"
  ],
  "license": "https://www.nist.gov/open/license",
  "modified": "2022-05-06 00:00:00",
  "programCode": [
    "006:045"
  ],
  "publisher": {
    "@type": "org:Organization",
    "name": "National Institute of Standards and Technology"
  },
  "references": [
    "https://dx.doi.org/10.1021/acsmacrolett.2c00369"
  ],
  "theme": [
    "Information Technology:Data and informatics",
    "Materials:Modeling and computational material science",
    "Materials:Polymers",
    "Mathematics and Statistics:Uncertainty quantification"
  ],
  "title": "Theory aware Machine Learning (TaML)"
}