Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "access_rights": "",
2
  "access_rights": "",
            
3
  "author": "Jesse Dodge",
3
  "author": "Jesse Dodge",
            
4
  "author_email": "",
4
  "author_email": "",
            
5
  "citation": [
5
  "citation": [
            
6
    "https://doi.org/10.1145/3539618.3592030",
6
    "https://doi.org/10.1145/3539618.3592030",
            
7
    "https://doi.org/10.48550/arXiv.2309.03004"
7
    "https://doi.org/10.48550/arXiv.2309.03004"
            
8
  ],
8
  ],
            
9
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
9
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
10
  "defined_in": "https://doi.org/10.48550/arXiv.2403.13485",
10
  "defined_in": "https://doi.org/10.48550/arXiv.2403.13485",
            
11
  "doi": "10.57702/0wpldwvq",
11
  "doi": "10.57702/0wpldwvq",
            
n
12
  "doi_date_published": null,
n
12
  "doi_date_published": "2024-12-03",
            
13
  "doi_publisher": "TIB",
13
  "doi_publisher": "TIB",
            
n
14
  "doi_status": false,
n
14
  "doi_status": true,
            
15
  "domain": "https://service.tib.eu/ldmservice",
15
  "domain": "https://service.tib.eu/ldmservice",
            
16
  "extra_authors": [
16
  "extra_authors": [
            
17
    {
17
    {
            
18
      "extra_author": "Maarten Sap",
18
      "extra_author": "Maarten Sap",
            
19
      "orcid": ""
19
      "orcid": ""
            
20
    },
20
    },
            
21
    {
21
    {
            
22
      "extra_author": "Ana Marasovi\u00b4c",
22
      "extra_author": "Ana Marasovi\u00b4c",
            
23
      "orcid": ""
23
      "orcid": ""
            
24
    },
24
    },
            
25
    {
25
    {
            
26
      "extra_author": "William Agnew",
26
      "extra_author": "William Agnew",
            
27
      "orcid": ""
27
      "orcid": ""
            
28
    },
28
    },
            
29
    {
29
    {
            
30
      "extra_author": "Gabriel Ilharco",
30
      "extra_author": "Gabriel Ilharco",
            
31
      "orcid": ""
31
      "orcid": ""
            
32
    },
32
    },
            
33
    {
33
    {
            
34
      "extra_author": "Dirk Groeneveld",
34
      "extra_author": "Dirk Groeneveld",
            
35
      "orcid": ""
35
      "orcid": ""
            
36
    },
36
    },
            
37
    {
37
    {
            
38
      "extra_author": "Margaret Mitchell",
38
      "extra_author": "Margaret Mitchell",
            
39
      "orcid": ""
39
      "orcid": ""
            
40
    },
40
    },
            
41
    {
41
    {
            
42
      "extra_author": "Matt Gardner",
42
      "extra_author": "Matt Gardner",
            
43
      "orcid": ""
43
      "orcid": ""
            
44
    }
44
    }
            
45
  ],
45
  ],
            
46
  "groups": [
46
  "groups": [
            
47
    {
47
    {
            
48
      "description": "",
48
      "description": "",
            
49
      "display_name": "Language Modeling",
49
      "display_name": "Language Modeling",
            
50
      "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
50
      "id": "f0c89329-f1ed-4ba3-90d2-5113fff9bf72",
            
51
      "image_display_url": "",
51
      "image_display_url": "",
            
52
      "name": "language-modeling",
52
      "name": "language-modeling",
            
53
      "title": "Language Modeling"
53
      "title": "Language Modeling"
            
54
    },
54
    },
            
55
    {
55
    {
            
56
      "description": "",
56
      "description": "",
            
57
      "display_name": "Natural Language Processing",
57
      "display_name": "Natural Language Processing",
            
58
      "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
58
      "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
            
59
      "image_display_url": "",
59
      "image_display_url": "",
            
60
      "name": "natural-language-processing",
60
      "name": "natural-language-processing",
            
61
      "title": "Natural Language Processing"
61
      "title": "Natural Language Processing"
            
62
    },
62
    },
            
63
    {
63
    {
            
64
      "description": "",
64
      "description": "",
            
65
      "display_name": "Text Classification",
65
      "display_name": "Text Classification",
            
66
      "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
66
      "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
            
67
      "image_display_url": "",
67
      "image_display_url": "",
            
68
      "name": "text-classification",
68
      "name": "text-classification",
            
69
      "title": "Text Classification"
69
      "title": "Text Classification"
            
70
    },
70
    },
            
71
    {
71
    {
            
72
      "description": "",
72
      "description": "",
            
73
      "display_name": "Text Generation",
73
      "display_name": "Text Generation",
            
74
      "id": "e9d4b27d-4658-4981-ac71-43ba61d3f4fb",
74
      "id": "e9d4b27d-4658-4981-ac71-43ba61d3f4fb",
            
75
      "image_display_url": "",
75
      "image_display_url": "",
            
76
      "name": "text-generation",
76
      "name": "text-generation",
            
77
      "title": "Text Generation"
77
      "title": "Text Generation"
            
78
    }
78
    }
            
79
  ],
79
  ],
            
80
  "id": "f3429369-60a8-43a9-876d-fa9dd98b4506",
80
  "id": "f3429369-60a8-43a9-876d-fa9dd98b4506",
            
81
  "isopen": false,
81
  "isopen": false,
            
82
  "landing_page": "https://huggingface.co/datasets/C4",
82
  "landing_page": "https://huggingface.co/datasets/C4",
            
83
  "license_title": null,
83
  "license_title": null,
            
84
  "link_orkg": "",
84
  "link_orkg": "",
            
85
  "metadata_created": "2024-12-03T07:39:37.814337",
85
  "metadata_created": "2024-12-03T07:39:37.814337",
            
n
86
  "metadata_modified": "2024-12-03T07:39:37.814343",
n
86
  "metadata_modified": "2024-12-03T07:39:38.285317",
            
87
  "name": "c4",
87
  "name": "c4",
            
88
  "notes": "The dataset used for pre-training language models, 
88
  "notes": "The dataset used for pre-training language models, 
            
89
containing a large collection of text documents.",
89
containing a large collection of text documents.",
            
n
90
  "num_resources": 0,
n
90
  "num_resources": 1,
            
91
  "num_tags": 9,
91
  "num_tags": 9,
            
92
  "organization": {
92
  "organization": {
            
93
    "approval_status": "approved",
93
    "approval_status": "approved",
            
94
    "created": "2024-11-25T12:11:38.292601",
94
    "created": "2024-11-25T12:11:38.292601",
            
95
    "description": "",
95
    "description": "",
            
96
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
96
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
97
    "image_url": "",
97
    "image_url": "",
            
98
    "is_organization": true,
98
    "is_organization": true,
            
99
    "name": "no-organization",
99
    "name": "no-organization",
            
100
    "state": "active",
100
    "state": "active",
            
101
    "title": "No Organization",
101
    "title": "No Organization",
            
102
    "type": "organization"
102
    "type": "organization"
            
103
  },
103
  },
            
104
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
104
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
105
  "private": false,
105
  "private": false,
            
106
  "relationships_as_object": [],
106
  "relationships_as_object": [],
            
107
  "relationships_as_subject": [],
107
  "relationships_as_subject": [],
            
t
108
  "resources": [],
t
108
  "resources": [
            
109
    {
            
110
      "cache_last_updated": null,
            
111
      "cache_url": null,
            
112
      "created": "2024-12-03T08:34:31",
            
113
      "data": [
            
114
        "dcterms:title",
            
115
        "dcterms:accessRights",
            
116
        "dcterms:creator",
            
117
        "dcterms:description",
            
118
        "dcterms:issued",
            
119
        "dcterms:language",
            
120
        "dcterms:identifier",
            
121
        "dcat:theme",
            
122
        "dcterms:type",
            
123
        "dcat:keyword",
            
124
        "dcat:landingPage",
            
125
        "dcterms:hasVersion",
            
126
        "dcterms:format",
            
127
        "mls:task",
            
128
        "datacite:isDescribedBy"
            
129
      ],
            
130
      "description": "The json representation of the dataset with its 
            
131
distributions based on DCAT.",
            
132
      "format": "JSON",
            
133
      "hash": "",
            
134
      "id": "9f28c3a2-ebd1-4e4a-a5e4-ee572b70bf39",
            
135
      "last_modified": "2024-12-03T07:39:38.277367",
            
136
      "metadata_modified": "2024-12-03T07:39:38.288205",
            
137
      "mimetype": "application/json",
            
138
      "mimetype_inner": null,
            
139
      "name": "Original Metadata",
            
140
      "package_id": "f3429369-60a8-43a9-876d-fa9dd98b4506",
            
141
      "position": 0,
            
142
      "resource_type": null,
            
143
      "size": 1120,
            
144
      "state": "active",
            
145
      "url": 
            
146
resource/9f28c3a2-ebd1-4e4a-a5e4-ee572b70bf39/download/metadata.json",
            
147
      "url_type": "upload"
            
148
    }
            
149
  ],
            
109
  "services_used_list": "",
150
  "services_used_list": "",
            
110
  "state": "active",
151
  "state": "active",
            
111
  "tags": [
152
  "tags": [
            
112
    {
153
    {
            
113
      "display_name": "Language Understanding",
154
      "display_name": "Language Understanding",
            
114
      "id": "865a0794-d6ce-4460-bb70-cfd801d43827",
155
      "id": "865a0794-d6ce-4460-bb70-cfd801d43827",
            
115
      "name": "Language Understanding",
156
      "name": "Language Understanding",
            
116
      "state": "active",
157
      "state": "active",
            
117
      "vocabulary_id": null
158
      "vocabulary_id": null
            
118
    },
159
    },
            
119
    {
160
    {
            
120
      "display_name": "Large-Scale Dataset",
161
      "display_name": "Large-Scale Dataset",
            
121
      "id": "f3f5ec8d-52e3-4bcf-84ee-2dbca89fc84a",
162
      "id": "f3f5ec8d-52e3-4bcf-84ee-2dbca89fc84a",
            
122
      "name": "Large-Scale Dataset",
163
      "name": "Large-Scale Dataset",
            
123
      "state": "active",
164
      "state": "active",
            
124
      "vocabulary_id": null
165
      "vocabulary_id": null
            
125
    },
166
    },
            
126
    {
167
    {
            
127
      "display_name": "dataset",
168
      "display_name": "dataset",
            
128
      "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b",
169
      "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b",
            
129
      "name": "dataset",
170
      "name": "dataset",
            
130
      "state": "active",
171
      "state": "active",
            
131
      "vocabulary_id": null
172
      "vocabulary_id": null
            
132
    },
173
    },
            
133
    {
174
    {
            
134
      "display_name": "evaluation",
175
      "display_name": "evaluation",
            
135
      "id": "cf6855c3-d4d5-44d1-a7ee-8168118d51cc",
176
      "id": "cf6855c3-d4d5-44d1-a7ee-8168118d51cc",
            
136
      "name": "evaluation",
177
      "name": "evaluation",
            
137
      "state": "active",
178
      "state": "active",
            
138
      "vocabulary_id": null
179
      "vocabulary_id": null
            
139
    },
180
    },
            
140
    {
181
    {
            
141
      "display_name": "language model",
182
      "display_name": "language model",
            
142
      "id": "d425459a-d1a3-4ace-95e4-e3aeb8c08293",
183
      "id": "d425459a-d1a3-4ace-95e4-e3aeb8c08293",
            
143
      "name": "language model",
184
      "name": "language model",
            
144
      "state": "active",
185
      "state": "active",
            
145
      "vocabulary_id": null
186
      "vocabulary_id": null
            
146
    },
187
    },
            
147
    {
188
    {
            
148
      "display_name": "language modeling",
189
      "display_name": "language modeling",
            
149
      "id": "44eb2c4c-e2cd-4698-bf3c-28ebbd5e3e42",
190
      "id": "44eb2c4c-e2cd-4698-bf3c-28ebbd5e3e42",
            
150
      "name": "language modeling",
191
      "name": "language modeling",
            
151
      "state": "active",
192
      "state": "active",
            
152
      "vocabulary_id": null
193
      "vocabulary_id": null
            
153
    },
194
    },
            
154
    {
195
    {
            
155
      "display_name": "text classification",
196
      "display_name": "text classification",
            
156
      "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d",
197
      "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d",
            
157
      "name": "text classification",
198
      "name": "text classification",
            
158
      "state": "active",
199
      "state": "active",
            
159
      "vocabulary_id": null
200
      "vocabulary_id": null
            
160
    },
201
    },
            
161
    {
202
    {
            
162
      "display_name": "text document",
203
      "display_name": "text document",
            
163
      "id": "17d386f1-2e02-410e-86ae-83a3aa8978af",
204
      "id": "17d386f1-2e02-410e-86ae-83a3aa8978af",
            
164
      "name": "text document",
205
      "name": "text document",
            
165
      "state": "active",
206
      "state": "active",
            
166
      "vocabulary_id": null
207
      "vocabulary_id": null
            
167
    },
208
    },
            
168
    {
209
    {
            
169
      "display_name": "text generation",
210
      "display_name": "text generation",
            
170
      "id": "064311a6-1694-4cd5-9b57-9a33271b140e",
211
      "id": "064311a6-1694-4cd5-9b57-9a33271b140e",
            
171
      "name": "text generation",
212
      "name": "text generation",
            
172
      "state": "active",
213
      "state": "active",
            
173
      "vocabulary_id": null
214
      "vocabulary_id": null
            
174
    }
215
    }
            
175
  ],
216
  ],
            
176
  "title": "C4",
217
  "title": "C4",
            
177
  "type": "dataset",
218
  "type": "dataset",
            
178
  "version": ""
219
  "version": ""
            
179
}
220
}