Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "access_rights": "",
2
  "access_rights": "",
            
3
  "author": "Ziyi Guan",
3
  "author": "Ziyi Guan",
            
4
  "author_email": "",
4
  "author_email": "",
            
5
  "citation": [
5
  "citation": [
            
6
    "https://doi.org/10.1145/3649329.3658498",
6
    "https://doi.org/10.1145/3649329.3658498",
            
7
    "https://doi.org/10.48550/arXiv.2203.06211"
7
    "https://doi.org/10.48550/arXiv.2203.06211"
            
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.2312.17295",
10
  "defined_in": "https://doi.org/10.48550/arXiv.2312.17295",
            
11
  "doi": "10.57702/bsbjlzeg",
11
  "doi": "10.57702/bsbjlzeg",
            
n
12
  "doi_date_published": null,
n
12
  "doi_date_published": "2024-12-16",
            
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": "Hantao Huang",
18
      "extra_author": "Hantao Huang",
            
19
      "orcid": ""
19
      "orcid": ""
            
20
    },
20
    },
            
21
    {
21
    {
            
22
      "extra_author": "Yupeng Su",
22
      "extra_author": "Yupeng Su",
            
23
      "orcid": ""
23
      "orcid": ""
            
24
    },
24
    },
            
25
    {
25
    {
            
26
      "extra_author": "Hong Huang",
26
      "extra_author": "Hong Huang",
            
27
      "orcid": ""
27
      "orcid": ""
            
28
    },
28
    },
            
29
    {
29
    {
            
30
      "extra_author": "Ngai Wong",
30
      "extra_author": "Ngai Wong",
            
31
      "orcid": ""
31
      "orcid": ""
            
32
    },
32
    },
            
33
    {
33
    {
            
34
      "extra_author": "Hao Yu",
34
      "extra_author": "Hao Yu",
            
35
      "orcid": ""
35
      "orcid": ""
            
36
    }
36
    }
            
37
  ],
37
  ],
            
38
  "groups": [
38
  "groups": [
            
39
    {
39
    {
            
40
      "description": "",
40
      "description": "",
            
41
      "display_name": "Large Language Models",
41
      "display_name": "Large Language Models",
            
42
      "id": "246be871-ce2b-4021-8290-df0f88dec833",
42
      "id": "246be871-ce2b-4021-8290-df0f88dec833",
            
43
      "image_display_url": "",
43
      "image_display_url": "",
            
44
      "name": "large-language-models",
44
      "name": "large-language-models",
            
45
      "title": "Large Language Models"
45
      "title": "Large Language Models"
            
46
    },
46
    },
            
47
    {
47
    {
            
48
      "description": "",
48
      "description": "",
            
49
      "display_name": "Natural Language Processing",
49
      "display_name": "Natural Language Processing",
            
50
      "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
50
      "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
            
51
      "image_display_url": "",
51
      "image_display_url": "",
            
52
      "name": "natural-language-processing",
52
      "name": "natural-language-processing",
            
53
      "title": "Natural Language Processing"
53
      "title": "Natural Language Processing"
            
54
    },
54
    },
            
55
    {
55
    {
            
56
      "description": "",
56
      "description": "",
            
57
      "display_name": "Text Classification",
57
      "display_name": "Text Classification",
            
58
      "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
58
      "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
            
59
      "image_display_url": "",
59
      "image_display_url": "",
            
60
      "name": "text-classification",
60
      "name": "text-classification",
            
61
      "title": "Text Classification"
61
      "title": "Text Classification"
            
62
    }
62
    }
            
63
  ],
63
  ],
            
64
  "id": "4cb89ea6-b6dc-4147-a737-55e5879d8591",
64
  "id": "4cb89ea6-b6dc-4147-a737-55e5879d8591",
            
65
  "isopen": false,
65
  "isopen": false,
            
66
  "landing_page": "https://huggingface.co/datasets/c4",
66
  "landing_page": "https://huggingface.co/datasets/c4",
            
67
  "license_title": null,
67
  "license_title": null,
            
68
  "link_orkg": "",
68
  "link_orkg": "",
            
69
  "metadata_created": "2024-12-16T19:39:38.133405",
69
  "metadata_created": "2024-12-16T19:39:38.133405",
            
n
70
  "metadata_modified": "2024-12-16T19:39:38.133411",
n
70
  "metadata_modified": "2024-12-16T19:39:38.493866",
            
71
  "name": "c4-dataset",
71
  "name": "c4-dataset",
            
72
  "notes": "The dataset used in the paper is not explicitly mentioned, 
72
  "notes": "The dataset used in the paper is not explicitly mentioned, 
            
73
but it is mentioned that the authors trained a GPT2 transformer 
73
but it is mentioned that the authors trained a GPT2 transformer 
            
74
language model on the C4 dataset.",
74
language model on the C4 dataset.",
            
n
75
  "num_resources": 0,
n
75
  "num_resources": 1,
            
76
  "num_tags": 6,
76
  "num_tags": 6,
            
77
  "organization": {
77
  "organization": {
            
78
    "approval_status": "approved",
78
    "approval_status": "approved",
            
79
    "created": "2024-11-25T12:11:38.292601",
79
    "created": "2024-11-25T12:11:38.292601",
            
80
    "description": "",
80
    "description": "",
            
81
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
81
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
82
    "image_url": "",
82
    "image_url": "",
            
83
    "is_organization": true,
83
    "is_organization": true,
            
84
    "name": "no-organization",
84
    "name": "no-organization",
            
85
    "state": "active",
85
    "state": "active",
            
86
    "title": "No Organization",
86
    "title": "No Organization",
            
87
    "type": "organization"
87
    "type": "organization"
            
88
  },
88
  },
            
89
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
89
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
90
  "private": false,
90
  "private": false,
            
91
  "relationships_as_object": [],
91
  "relationships_as_object": [],
            
92
  "relationships_as_subject": [],
92
  "relationships_as_subject": [],
            
t
93
  "resources": [],
t
93
  "resources": [
            
94
    {
            
95
      "cache_last_updated": null,
            
96
      "cache_url": null,
            
97
      "created": "2024-12-16T18:25:42",
            
98
      "data": [
            
99
        "dcterms:title",
            
100
        "dcterms:accessRights",
            
101
        "dcterms:creator",
            
102
        "dcterms:description",
            
103
        "dcterms:issued",
            
104
        "dcterms:language",
            
105
        "dcterms:identifier",
            
106
        "dcat:theme",
            
107
        "dcterms:type",
            
108
        "dcat:keyword",
            
109
        "dcat:landingPage",
            
110
        "dcterms:hasVersion",
            
111
        "dcterms:format",
            
112
        "mls:task",
            
113
        "datacite:isDescribedBy"
            
114
      ],
            
115
      "description": "The json representation of the dataset with its 
            
116
distributions based on DCAT.",
            
117
      "format": "JSON",
            
118
      "hash": "",
            
119
      "id": "831b4ca6-8f93-4346-9f01-4c7b03636d44",
            
120
      "last_modified": "2024-12-16T19:39:38.486408",
            
121
      "metadata_modified": "2024-12-16T19:39:38.496677",
            
122
      "mimetype": "application/json",
            
123
      "mimetype_inner": null,
            
124
      "name": "Original Metadata",
            
125
      "package_id": "4cb89ea6-b6dc-4147-a737-55e5879d8591",
            
126
      "position": 0,
            
127
      "resource_type": null,
            
128
      "size": 999,
            
129
      "state": "active",
            
130
      "url": 
            
131
resource/831b4ca6-8f93-4346-9f01-4c7b03636d44/download/metadata.json",
            
132
      "url_type": "upload"
            
133
    }
            
134
  ],
            
94
  "services_used_list": "",
135
  "services_used_list": "",
            
95
  "state": "active",
136
  "state": "active",
            
96
  "tags": [
137
  "tags": [
            
97
    {
138
    {
            
98
      "display_name": "C4 dataset",
139
      "display_name": "C4 dataset",
            
99
      "id": "8a864899-bed7-4eb0-816f-e7265a37bf07",
140
      "id": "8a864899-bed7-4eb0-816f-e7265a37bf07",
            
100
      "name": "C4 dataset",
141
      "name": "C4 dataset",
            
101
      "state": "active",
142
      "state": "active",
            
102
      "vocabulary_id": null
143
      "vocabulary_id": null
            
103
    },
144
    },
            
104
    {
145
    {
            
105
      "display_name": "GPT2",
146
      "display_name": "GPT2",
            
106
      "id": "51b3703c-f073-4c26-96ef-fe55af0e034f",
147
      "id": "51b3703c-f073-4c26-96ef-fe55af0e034f",
            
107
      "name": "GPT2",
148
      "name": "GPT2",
            
108
      "state": "active",
149
      "state": "active",
            
109
      "vocabulary_id": null
150
      "vocabulary_id": null
            
110
    },
151
    },
            
111
    {
152
    {
            
112
      "display_name": "Large Language Models",
153
      "display_name": "Large Language Models",
            
113
      "id": "6e366b4a-402d-4c0e-b818-6fec429fc72f",
154
      "id": "6e366b4a-402d-4c0e-b818-6fec429fc72f",
            
114
      "name": "Large Language Models",
155
      "name": "Large Language Models",
            
115
      "state": "active",
156
      "state": "active",
            
116
      "vocabulary_id": null
157
      "vocabulary_id": null
            
117
    },
158
    },
            
118
    {
159
    {
            
119
      "display_name": "news articles",
160
      "display_name": "news articles",
            
120
      "id": "1a135fb9-451c-43c3-8e50-56e12fecd892",
161
      "id": "1a135fb9-451c-43c3-8e50-56e12fecd892",
            
121
      "name": "news articles",
162
      "name": "news articles",
            
122
      "state": "active",
163
      "state": "active",
            
123
      "vocabulary_id": null
164
      "vocabulary_id": null
            
124
    },
165
    },
            
125
    {
166
    {
            
126
      "display_name": "text classification",
167
      "display_name": "text classification",
            
127
      "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d",
168
      "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d",
            
128
      "name": "text classification",
169
      "name": "text classification",
            
129
      "state": "active",
170
      "state": "active",
            
130
      "vocabulary_id": null
171
      "vocabulary_id": null
            
131
    },
172
    },
            
132
    {
173
    {
            
133
      "display_name": "transformer language model",
174
      "display_name": "transformer language model",
            
134
      "id": "c0d2674d-2a7f-4ea1-aef5-ea4e1cc0a5e7",
175
      "id": "c0d2674d-2a7f-4ea1-aef5-ea4e1cc0a5e7",
            
135
      "name": "transformer language model",
176
      "name": "transformer language model",
            
136
      "state": "active",
177
      "state": "active",
            
137
      "vocabulary_id": null
178
      "vocabulary_id": null
            
138
    }
179
    }
            
139
  ],
180
  ],
            
140
  "title": "C4 dataset",
181
  "title": "C4 dataset",
            
141
  "type": "dataset",
182
  "type": "dataset",
            
142
  "version": ""
183
  "version": ""
            
143
}
184
}