Technical note Open Access

A Dataset for GitHub Repository Deduplication: Extended Description

Spinellis, Diomidis; Kotti, Zoe; Mockus, Audris


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/b04a9e19-8fa7-414a-bd14-40212ecbd286/forkproj-extended.pdf"
      }, 
      "checksum": "md5:c3791f1707a97d5e3a25fe8bd662c165", 
      "bucket": "b04a9e19-8fa7-414a-bd14-40212ecbd286", 
      "key": "forkproj-extended.pdf", 
      "type": "pdf", 
      "size": 1836423
    }
  ], 
  "owners": [
    57930
  ], 
  "doi": "10.5281/zenodo.3740595", 
  "stats": {
    "version_unique_downloads": 164.0, 
    "unique_views": 318.0, 
    "views": 351.0, 
    "version_views": 351.0, 
    "unique_downloads": 164.0, 
    "version_unique_views": 318.0, 
    "volume": 328719717.0, 
    "version_downloads": 179.0, 
    "downloads": 179.0, 
    "version_volume": 328719717.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3740595", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3740594", 
    "bucket": "https://zenodo.org/api/files/b04a9e19-8fa7-414a-bd14-40212ecbd286", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3740594.svg", 
    "html": "https://zenodo.org/record/3740595", 
    "latest_html": "https://zenodo.org/record/3740595", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3740595.svg", 
    "latest": "https://zenodo.org/api/records/3740595"
  }, 
  "conceptdoi": "10.5281/zenodo.3740594", 
  "created": "2020-04-08T17:56:41.841616+00:00", 
  "updated": "2020-04-21T10:11:04.489046+00:00", 
  "conceptrecid": "3740594", 
  "revision": 3, 
  "id": 3740595, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3740595", 
    "description": "<p>GitHub projects can be easily replicated through the site&#39;s fork<br>\nprocess or through a Git clone-push sequence.&nbsp; This is a problem for<br>\nempirical software engineering, because it can lead to skewed results<br>\nor mistrained machine learning models.&nbsp; We provide a dataset of 10.6<br>\nmillion GitHub projects that are copies of others, and link each record<br>\nwith the project&#39;s ultimate parent.&nbsp; The ultimate parents were derived<br>\nfrom a ranking along six metrics.&nbsp; The related projects were calculated<br>\nas the connected components of an 18.2 million node and 12 million<br>\nedge denoised graph created by directing edges to ultimate parents.<br>\nThe graph was created by filtering out more than 30 hand-picked and 2.3<br>\nmillion pattern-matched clumping projects.&nbsp; Projects that introduced<br>\nunwanted clumping were identified by repeatedly visualizing shortest path<br>\ndistances between unrelated important projects.&nbsp; Our dataset identified<br>\n30 thousand duplicate projects in an existing popular reference dataset<br>\nof 1.8 million projects.&nbsp; An evaluation of our dataset against another<br>\ncreated independently with different methods found a significant overlap,<br>\nbut also differences attributed to the operational definition of what<br>\nprojects are considered as related.</p>\n\n<p>&nbsp;</p>", 
    "language": "eng", 
    "title": "A Dataset for GitHub Repository Deduplication: Extended Description", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3740594"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3740595"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "825328", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::825328"
        }, 
        "title": "Fine-Grained Analysis of Software Ecosystems as Networks", 
        "acronym": "FASTEN", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "deduplication", 
      "fork", 
      "project clone", 
      "GitHub", 
      "dataset"
    ], 
    "publication_date": "2020-04-21", 
    "creators": [
      {
        "orcid": "0000-0003-4231-1897", 
        "affiliation": "Athens University of Economics and Business", 
        "name": "Spinellis, Diomidis"
      }, 
      {
        "orcid": "0000-0003-3816-9162", 
        "affiliation": "Athens University of Economics and Business", 
        "name": "Kotti, Zoe"
      }, 
      {
        "affiliation": "University of Tennessee", 
        "name": "Mockus, Audris"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "technicalnote", 
      "type": "publication", 
      "title": "Technical note"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.1145/3379597.3387496", 
        "relation": "isSupplementTo", 
        "resource_type": "publication-conferencepaper"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.1145/3379597.3387496", 
        "relation": "isCitedBy", 
        "resource_type": "publication-conferencepaper"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3653924", 
        "relation": "documents", 
        "resource_type": "software"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3653920", 
        "relation": "documents", 
        "resource_type": "dataset"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3740594", 
        "relation": "isVersionOf"
      }
    ]
  }
}
351
179
views
downloads
All versions This version
Views 351351
Downloads 179179
Data volume 328.7 MB328.7 MB
Unique views 318318
Unique downloads 164164

Share

Cite as