Dataset Open Access

Reliance on Science in Patenting

Marx, Matt; Aaron Fuegi


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/authoridname_normalized.zip"
      }, 
      "checksum": "md5:9baea14de6e6ed5bad514dfb7b005d4b", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "authoridname_normalized.zip", 
      "type": "zip", 
      "size": 2911413577
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/bodytextknowngood.tsv"
      }, 
      "checksum": "md5:0d20284aadeb443ad48eac1d00ae503f", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "bodytextknowngood.tsv", 
      "type": "tsv", 
      "size": 272069
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/conferenceidname.zip"
      }, 
      "checksum": "md5:ea4aabd9bd31834f7ec333f0ff09bae3", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "conferenceidname.zip", 
      "type": "zip", 
      "size": 82506
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/__datadescription.pdf"
      }, 
      "checksum": "md5:24a62a8cc9aeb11dbec4772b9b2ea9e6", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "__datadescription.pdf", 
      "type": "pdf", 
      "size": 214481
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/intlpatfamily.zip"
      }, 
      "checksum": "md5:5bb26fd59a0f9b9e2a44a4a124d44b6c", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "intlpatfamily.zip", 
      "type": "zip", 
      "size": 1020546913
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/jcif.zip"
      }, 
      "checksum": "md5:c2f351238565d2216136aeaacdf55914", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "jcif.zip", 
      "type": "zip", 
      "size": 5224591
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/jif.zip"
      }, 
      "checksum": "md5:7c66b0a4d51721179ce103ce9fdb35c9", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "jif.zip", 
      "type": "zip", 
      "size": 8123343
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/journalidnameissn.zip"
      }, 
      "checksum": "md5:10caa9741ef18909a421e9d4b0ec7f9d", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "journalidnameissn.zip", 
      "type": "zip", 
      "size": 1536445
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/magfield_oecd_wos_crosswalk.zip"
      }, 
      "checksum": "md5:bbe297e3f6a71b79d3b754ab00c3eba0", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "magfield_oecd_wos_crosswalk.zip", 
      "type": "zip", 
      "size": 2166111020
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/paperauthoridaffiliationname.zip"
      }, 
      "checksum": "md5:9c554f94e8f40d3c790219d0a3eb31cc", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "paperauthoridaffiliationname.zip", 
      "type": "zip", 
      "size": 5412724615
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/paperauthororder.zip"
      }, 
      "checksum": "md5:7f0cd9e741d74eb71e36ba40ecdeb6b9", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "paperauthororder.zip", 
      "type": "zip", 
      "size": 4101554649
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/papercitations.zip"
      }, 
      "checksum": "md5:efe102008ad67d05bbab4f54af127e89", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "papercitations.zip", 
      "type": "zip", 
      "size": 9888369890
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/paperconferenceid.zip"
      }, 
      "checksum": "md5:aa8f5aed09f77ddfe0d92a6e9a174b88", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "paperconferenceid.zip", 
      "type": "zip", 
      "size": 519179792
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/paperjournalid.zip"
      }, 
      "checksum": "md5:fcdffdcaf89eafe8f0a8fdc76605cdae", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "paperjournalid.zip", 
      "type": "zip", 
      "size": 920631181
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/papertitle.zip"
      }, 
      "checksum": "md5:827f82924c589774dacb6b4fc086aad7", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "papertitle.zip", 
      "type": "zip", 
      "size": 8103221095
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/papervolisspages.zip"
      }, 
      "checksum": "md5:c293eb5be22c57a4b0cf2ba910218245", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "papervolisspages.zip", 
      "type": "zip", 
      "size": 1274560857
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/paperyear.zip"
      }, 
      "checksum": "md5:26e196c99224556f27e941b80fdb5e70", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "paperyear.zip", 
      "type": "zip", 
      "size": 710707522
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291/_pcs_mag_doi_pmid.tsv"
      }, 
      "checksum": "md5:4238c739a4c52ef15507436adc79ac23", 
      "bucket": "53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
      "key": "_pcs_mag_doi_pmid.tsv", 
      "type": "tsv", 
      "size": 2754045930
    }
  ], 
  "owners": [
    68428
  ], 
  "doi": "10.5281/zenodo.5111261", 
  "stats": {
    "version_unique_downloads": 13216.0, 
    "unique_views": 258.0, 
    "views": 295.0, 
    "version_views": 22371.0, 
    "unique_downloads": 192.0, 
    "version_unique_views": 18156.0, 
    "volume": 347175718311.0, 
    "version_downloads": 37407.0, 
    "downloads": 282.0, 
    "version_volume": 113307856872243.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.5111261", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3236339", 
    "bucket": "https://zenodo.org/api/files/53159f22-0bf5-4a62-a7dc-80eb8f29d291", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3236339.svg", 
    "html": "https://zenodo.org/record/5111261", 
    "latest_html": "https://zenodo.org/record/5111261", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.5111261.svg", 
    "latest": "https://zenodo.org/api/records/5111261"
  }, 
  "conceptdoi": "10.5281/zenodo.3236339", 
  "created": "2021-07-17T05:41:04.504739+00:00", 
  "updated": "2021-07-20T13:28:13.177845+00:00", 
  "conceptrecid": "3236339", 
  "revision": 4, 
  "id": 5111261, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.5111261", 
    "description": "<p><em><strong>Note: If you downloaded these data between May 29 (v30) and July 16 (v31), please delete those and replace them with the current release below&nbsp;(v32, uploaded July 17). I introduced a bug with v30 that resulted in duplicate patent-paper linkages due to erroneous patent numberings.&nbsp;</strong></em></p>\n\n<p>This dataset contains both front-page and in-text citations from patents to scientific articles through 2020. &nbsp;<em>If you use the data, please cite </em>these two articles:</p>\n\n<p><strong>1. M. Marx, &amp; A.&nbsp;Fuegi, &quot;Reliance on Science: Worldwide Front-Page Patent Citations to Scientific Articles&quot; (2020),&nbsp;<em>Strategic Management Journal 41(9):1572-1594</em>. (</strong><a href=\"https://onlinelibrary.wiley.com/doi/full/10.1002/smj.3145\">https://onlinelibrary.wiley.com/doi/full/10.1002/smj.3145</a><strong>)&nbsp;</strong></p>\n\n<p><strong>2. M. Marx &amp; A. Fuegi, &quot;Reliance on Science by Inventors: Hybrid Extraction of In-text Patent-to-Article Citations.&quot; NBER Working Paper&nbsp;27987</strong>.(<a href=\"https://www.nber.org/papers/w27987\">https://www.nber.org/papers/w27987</a>)</p>\n\n<p>The datafile containing the citations is <strong>_pcs_mag_doi_pmid.tsv.&nbsp;</strong>DOIs and PMIDs provided where available. Each citation has the&nbsp;applicant/examiner flag, confidence score&nbsp;(1-10), and&nbsp;whether the reference was a) only on the front page, b) only in the body text, or c) in both.&nbsp;<strong>_data_description.pdf</strong>&nbsp;has full details.&nbsp;<strong>bodytextknowngood.tsv</strong>&nbsp;contains the known-good references for calculating recall.</p>\n\n<p>The remaining files redistribute the&nbsp;<a href=\"http://aka.ms/msracad\">Microsoft Academic Graph</a>. Please also cite&nbsp;Sinha, A, et al. 2015. Overview of Microsoft Academic Service (MAS) and Applications. In Proceedings of the 24th International Conference on World Wide Web (WWW &rsquo;15 Companion). ACM, New York, NY, USA, 243-246.</p>\n\n<p>These data are under an&nbsp;Open Data Commons Attribution license (ODC-By);&nbsp;use them for anything&nbsp;as long as you cite us! Source code for front-page matches is at&nbsp;https://github.com/mattmarx/reliance_on_science&nbsp;and for in-text is at https://github.com/mattmarx/intextcitations. Questions &amp; feedback to <a href=\"mailto:support@relianceonscience.org\">support@relianceonscience.org</a><em>.</em></p>\n\n<p><strong><em>This work is sponsored by the Alfred P. Sloan Foundation grant #G-2021-16822.</em></strong></p>", 
    "language": "eng", 
    "title": "Reliance on Science in Patenting", 
    "license": {
      "id": "ODC-By-1.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 44, 
          "index": 43, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3236339"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5111261"
          }
        }
      ]
    }, 
    "version": "v32", 
    "references": [
      "Marx, Matt and Aaron Fuegi, \"Reliance on Science in Patenting: USPTO Front-Page Citations to Scientific Articles\" (https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3331686)", 
      "Sinha, Arnab, Zhihong Shen, Yang Song, Hao Ma, Darrin Eide, Bo-June (Paul) Hsu, and Kuansan Wang. 2015. An Overview of Microsoft Academic Service (MAS) and Applications. In Proceedings of the 24th International Conference on World Wide Web (WWW '15 Companion). ACM, New York, NY, USA, 243-246"
    ], 
    "keywords": [
      "innovation, patenting, science, citation"
    ], 
    "publication_date": "2021-07-17", 
    "creators": [
      {
        "orcid": "0000-0002-6173-4142", 
        "affiliation": "Cornell University", 
        "name": "Marx, Matt"
      }, 
      {
        "affiliation": "Boston University", 
        "name": "Aaron Fuegi"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3236339", 
        "relation": "isVersionOf"
      }
    ]
  }
}
22,371
37,407
views
downloads
All versions This version
Views 22,371295
Downloads 37,407282
Data volume 113.3 TB347.2 GB
Unique views 18,156258
Unique downloads 13,216192

Share

Cite as