Dataset Open Access

DIRE: A Neural Approach to Decompiled Identifier Naming

Lacomis, Jeremy; Yin, Pengcheng; Schwartz, Edward J.; Allamanis, Miltiadis; Le Goues, Claire; Neubig, Graham; Vasilescu, Bogdan


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/0-trees.tar.bz2"
      }, 
      "checksum": "md5:f6f50e591e0b87286adf4037db5c5326", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "0-trees.tar.bz2", 
      "type": "bz2", 
      "size": 151230337
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/0-trees.tar.gz"
      }, 
      "checksum": "md5:b2b9e5b6d9804ee0dd5e512e2fb1b886", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "0-trees.tar.gz", 
      "type": "gz", 
      "size": 250808987
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/1-trees.tar.bz2"
      }, 
      "checksum": "md5:22725b6a13a581fd11939d9f0d9755d2", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "1-trees.tar.bz2", 
      "type": "bz2", 
      "size": 151843136
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/1-trees.tar.gz"
      }, 
      "checksum": "md5:2b8ae5d693fad500f0fd0b59b50d8d81", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "1-trees.tar.gz", 
      "type": "gz", 
      "size": 251823084
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/2-trees.tar.bz2"
      }, 
      "checksum": "md5:90d57fe8d1e0e7c5c965e29cce752388", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "2-trees.tar.bz2", 
      "type": "bz2", 
      "size": 156967905
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/2-trees.tar.gz"
      }, 
      "checksum": "md5:c80d48c918a1c7e8b60789691cda21cd", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "2-trees.tar.gz", 
      "type": "gz", 
      "size": 259715957
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/3-trees.tar.bz2"
      }, 
      "checksum": "md5:d86ae421c9628b5fc6bdfe0b60bc8997", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "3-trees.tar.bz2", 
      "type": "bz2", 
      "size": 166775905
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/3-trees.tar.gz"
      }, 
      "checksum": "md5:03326d0d4300579efbd6e233be3b99bd", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "3-trees.tar.gz", 
      "type": "gz", 
      "size": 276902594
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/4-trees.tar.bz2"
      }, 
      "checksum": "md5:e1448edff59ad43e81ca572ed5b9321c", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "4-trees.tar.bz2", 
      "type": "bz2", 
      "size": 163880520
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/4-trees.tar.gz"
      }, 
      "checksum": "md5:98cb8057b336d6cb8beea88de84fbac1", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "4-trees.tar.gz", 
      "type": "gz", 
      "size": 271029988
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/5-trees.tar.bz2"
      }, 
      "checksum": "md5:236626301caa357b21806acc319b02e6", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "5-trees.tar.bz2", 
      "type": "bz2", 
      "size": 152969118
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/5-trees.tar.gz"
      }, 
      "checksum": "md5:9b4f94607335772b044c62d647aba6cf", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "5-trees.tar.gz", 
      "type": "gz", 
      "size": 253704126
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/6-trees.tar.gz"
      }, 
      "checksum": "md5:504a7bae05a79a1e9b417cdb24644ea7", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "6-trees.tar.gz", 
      "type": "gz", 
      "size": 264222818
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/7-trees.tar.bz2"
      }, 
      "checksum": "md5:dbaed7f3096ed4a5ef90c5facf48be75", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "7-trees.tar.bz2", 
      "type": "bz2", 
      "size": 150681017
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/7-trees.tar.gz"
      }, 
      "checksum": "md5:b7347771c5ffd40d33857e66114d68ff", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "7-trees.tar.gz", 
      "type": "gz", 
      "size": 249912588
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/8-trees.tar.bz2"
      }, 
      "checksum": "md5:bc480a2bee0bd3212937d512dd992c34", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "8-trees.tar.bz2", 
      "type": "bz2", 
      "size": 156188339
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/8-trees.tar.gz"
      }, 
      "checksum": "md5:c7672cc3575db9760da635f58d6e441d", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "8-trees.tar.gz", 
      "type": "gz", 
      "size": 258967964
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/9-trees.tar.bz2"
      }, 
      "checksum": "md5:7e8c1d75838252154d76eec139e2e4d7", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "9-trees.tar.bz2", 
      "type": "bz2", 
      "size": 157659741
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/9-trees.tar.gz"
      }, 
      "checksum": "md5:ff8f29e381078c77bd3164138302ad0a", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "9-trees.tar.gz", 
      "type": "gz", 
      "size": 260969987
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/a-trees.tar.bz2"
      }, 
      "checksum": "md5:8140925c954a99f925049633fb7a5a64", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "a-trees.tar.bz2", 
      "type": "bz2", 
      "size": 154214127
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/a-trees.tar.gz"
      }, 
      "checksum": "md5:d3b65c7aea71a146f0631c52f7424f05", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "a-trees.tar.gz", 
      "type": "gz", 
      "size": 255339718
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/b-trees.tar.bz2"
      }, 
      "checksum": "md5:e6c3e05f761d996c2032a76169a018b6", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "b-trees.tar.bz2", 
      "type": "bz2", 
      "size": 155353559
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/b-trees.tar.gz"
      }, 
      "checksum": "md5:9d74988a8e928a9122166deb4a21e90c", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "b-trees.tar.gz", 
      "type": "gz", 
      "size": 257559022
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/c-trees.tar.bz2"
      }, 
      "checksum": "md5:307a08acef47c35e5a489d5afab0ddcd", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "c-trees.tar.bz2", 
      "type": "bz2", 
      "size": 163501721
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/c-trees.tar.gz"
      }, 
      "checksum": "md5:05dc395dbf51303e1ef38e71f5249ca9", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "c-trees.tar.gz", 
      "type": "gz", 
      "size": 271945668
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/d-trees.tar.bz2"
      }, 
      "checksum": "md5:f7ad3caabad2b0a2ec8e204ebde2e609", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "d-trees.tar.bz2", 
      "type": "bz2", 
      "size": 162543223
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/d-trees.tar.gz"
      }, 
      "checksum": "md5:1c666f3b20ba0403d5d0ec261ebc03b7", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "d-trees.tar.gz", 
      "type": "gz", 
      "size": 269678426
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/e-trees.tar.bz2"
      }, 
      "checksum": "md5:89ab0e0fe48f283ec642e69ddddc8e35", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "e-trees.tar.bz2", 
      "type": "bz2", 
      "size": 155956013
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/e-trees.tar.gz"
      }, 
      "checksum": "md5:7b57706ec9a2948cc2ae3b45353090aa", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "e-trees.tar.gz", 
      "type": "gz", 
      "size": 257935192
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/f-trees.tar.bz2"
      }, 
      "checksum": "md5:681666c06d9e43093fa4c50dbbfecb4a", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "f-trees.tar.bz2", 
      "type": "bz2", 
      "size": 150117126
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/f-trees.tar.gz"
      }, 
      "checksum": "md5:ae0ecd96ef96cccc0e2340f757d8bdcf", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "f-trees.tar.gz", 
      "type": "gz", 
      "size": 249195409
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6/README"
      }, 
      "checksum": "md5:ce1c12d7b5072c540e1ffea48bd78e0b", 
      "bucket": "0c954e19-732e-4912-b582-6d1d35df54e6", 
      "key": "README", 
      "type": "", 
      "size": 935
    }
  ], 
  "owners": [
    76681
  ], 
  "doi": "10.5281/zenodo.3403078", 
  "stats": {
    "version_unique_downloads": 347.0, 
    "unique_views": 482.0, 
    "views": 546.0, 
    "version_views": 546.0, 
    "unique_downloads": 347.0, 
    "version_unique_views": 482.0, 
    "volume": 846134420981.0, 
    "version_downloads": 5059.0, 
    "downloads": 5059.0, 
    "version_volume": 846134420981.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3403078", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3403077", 
    "bucket": "https://zenodo.org/api/files/0c954e19-732e-4912-b582-6d1d35df54e6", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3403077.svg", 
    "html": "https://zenodo.org/record/3403078", 
    "latest_html": "https://zenodo.org/record/3403078", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3403078.svg", 
    "latest": "https://zenodo.org/api/records/3403078"
  }, 
  "conceptdoi": "10.5281/zenodo.3403077", 
  "created": "2019-09-09T17:17:14.370641+00:00", 
  "updated": "2020-01-24T19:25:12.444168+00:00", 
  "conceptrecid": "3403077", 
  "revision": 4, 
  "id": 3403078, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3403078", 
    "description": "<p>This dataset is released as a companion to the paper &quot;DIRE: A Neural Approach to Decompiled Identifier Naming&quot;, appearing in the proceedings of the&nbsp;34th IEEE/ACM International Conference on Automated Software Engineering (ASE 2019).</p>\n\n<p>It contains information generated by decompiling 3,195,962 functions found in 164,632 unique binaries generated from C code scraped from GitHub. For practicality, the dataset is partitioned into 16 archives by the first hexadecimal digit of the SHA-256 hash of the binary used to generate it. Each of the 16 archives contains approximately 10,000&nbsp;JSONL files, named according to a binary&#39;s hash. Each JSONL file consists of a single JSON object per-line corresponding to a single function in the decompiled binary.</p>\n\n<p>Archives are provided in both GZIP and BZIP2 format.</p>\n\n<p>See the README file for more information.</p>", 
    "license": {
      "id": "MIT"
    }, 
    "title": "DIRE: A Neural Approach to Decompiled Identifier Naming", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3403077"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3403078"
          }
        }
      ]
    }, 
    "publication_date": "2019-09-09", 
    "creators": [
      {
        "orcid": "0000-0003-0653-5738", 
        "affiliation": "Carnegie Mellon University", 
        "name": "Lacomis, Jeremy"
      }, 
      {
        "affiliation": "Carnegie Mellon University", 
        "name": "Yin, Pengcheng"
      }, 
      {
        "affiliation": "Carnegie Mellon University Software Engineering Institute", 
        "name": "Schwartz, Edward J."
      }, 
      {
        "affiliation": "Microsoft Research", 
        "name": "Allamanis, Miltiadis"
      }, 
      {
        "affiliation": "Carnegie Mellon University", 
        "name": "Le Goues, Claire"
      }, 
      {
        "affiliation": "Carnegie Mellon University", 
        "name": "Neubig, Graham"
      }, 
      {
        "affiliation": "Carnegie Mellon University", 
        "name": "Vasilescu, Bogdan"
      }
    ], 
    "meeting": {
      "acronym": "ASE", 
      "title": "International Conference on Automated Software Engineering"
    }, 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3403077", 
        "relation": "isVersionOf"
      }
    ]
  }
}
546
5,059
views
downloads
All versions This version
Views 546546
Downloads 5,0595,059
Data volume 846.1 GB846.1 GB
Unique views 482482
Unique downloads 347347

Share

Cite as