Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "access_rights": "",
2
  "access_rights": "",
            
3
  "author": "Julien Launay",
3
  "author": "Julien Launay",
            
4
  "author_email": "",
4
  "author_email": "",
            
5
  "citation": [],
5
  "citation": [],
            
6
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
6
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
7
  "defined_in": "https://doi.org/10.48550/arXiv.2302.04761",
7
  "defined_in": "https://doi.org/10.48550/arXiv.2302.04761",
            
8
  "doi": "10.57702/ud3pyqy2",
8
  "doi": "10.57702/ud3pyqy2",
            
9
  "doi_date_published": "2024-12-02",
9
  "doi_date_published": "2024-12-02",
            
10
  "doi_publisher": "TIB",
10
  "doi_publisher": "TIB",
            
11
  "doi_status": true,
11
  "doi_status": true,
            
12
  "domain": "https://service.tib.eu/ldmservice",
12
  "domain": "https://service.tib.eu/ldmservice",
            
13
  "extra_authors": [
13
  "extra_authors": [
            
14
    {
14
    {
            
15
      "extra_author": "Elena Tommasone",
15
      "extra_author": "Elena Tommasone",
            
16
      "orcid": ""
16
      "orcid": ""
            
17
    },
17
    },
            
18
    {
18
    {
            
19
      "extra_author": "Baptiste Pannier",
19
      "extra_author": "Baptiste Pannier",
            
20
      "orcid": ""
20
      "orcid": ""
            
21
    },
21
    },
            
22
    {
22
    {
            
23
      "extra_author": "Fran\u00e7ois Boniface",
23
      "extra_author": "Fran\u00e7ois Boniface",
            
24
      "orcid": ""
24
      "orcid": ""
            
25
    },
25
    },
            
26
    {
26
    {
            
27
      "extra_author": "Am\u00e9lie Chatelain",
27
      "extra_author": "Am\u00e9lie Chatelain",
            
28
      "orcid": ""
28
      "orcid": ""
            
29
    },
29
    },
            
30
    {
30
    {
            
31
      "extra_author": "Alessandro Cappelli",
31
      "extra_author": "Alessandro Cappelli",
            
32
      "orcid": ""
32
      "orcid": ""
            
33
    },
33
    },
            
34
    {
34
    {
            
35
      "extra_author": "Iacopo Poli",
35
      "extra_author": "Iacopo Poli",
            
36
      "orcid": ""
36
      "orcid": ""
            
37
    },
37
    },
            
38
    {
38
    {
            
39
      "extra_author": "Djam\u00e9 Seddah",
39
      "extra_author": "Djam\u00e9 Seddah",
            
40
      "orcid": ""
40
      "orcid": ""
            
41
    }
41
    }
            
42
  ],
42
  ],
            
43
  "groups": [
43
  "groups": [
            
44
    {
44
    {
            
45
      "description": "",
45
      "description": "",
            
46
      "display_name": "Natural Language Processing",
46
      "display_name": "Natural Language Processing",
            
47
      "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
47
      "id": "5b974bcc-8f79-40fc-a05d-75b861d55ed0",
            
48
      "image_display_url": "",
48
      "image_display_url": "",
            
49
      "name": "natural-language-processing",
49
      "name": "natural-language-processing",
            
50
      "title": "Natural Language Processing"
50
      "title": "Natural Language Processing"
            
51
    },
51
    },
            
52
    {
52
    {
            
53
      "description": "",
53
      "description": "",
            
54
      "display_name": "Text Data",
54
      "display_name": "Text Data",
            
55
      "id": "30d52e93-891a-463b-a577-99a00396f012",
55
      "id": "30d52e93-891a-463b-a577-99a00396f012",
            
56
      "image_display_url": "",
56
      "image_display_url": "",
            
57
      "name": "text-data",
57
      "name": "text-data",
            
58
      "title": "Text Data"
58
      "title": "Text Data"
            
59
    }
59
    }
            
60
  ],
60
  ],
            
61
  "id": "8b69e6ea-d51d-4a11-8054-8e82e1522d9a",
61
  "id": "8b69e6ea-d51d-4a11-8054-8e82e1522d9a",
            
62
  "isopen": false,
62
  "isopen": false,
            
63
  "landing_page": "https://commoncrawl.org/",
63
  "landing_page": "https://commoncrawl.org/",
            
64
  "license_title": null,
64
  "license_title": null,
            
65
  "link_orkg": "http://orkg.org/orkg/resource/R642948",
65
  "link_orkg": "http://orkg.org/orkg/resource/R642948",
            
66
  "metadata_created": "2024-12-02T18:01:56.927025",
66
  "metadata_created": "2024-12-02T18:01:56.927025",
            
n
67
  "metadata_modified": "2024-12-02T18:01:56.984474",
n
67
  "metadata_modified": "2024-12-02T18:01:58.242715",
            
68
  "name": "ccnet",
68
  "name": "ccnet",
            
69
  "notes": "The dataset used in the paper to train the Toolformer 
69
  "notes": "The dataset used in the paper to train the Toolformer 
            
70
model.",
70
model.",
            
n
71
  "num_resources": 0,
n
71
  "num_resources": 1,
            
72
  "num_tags": 5,
72
  "num_tags": 5,
            
73
  "organization": {
73
  "organization": {
            
74
    "approval_status": "approved",
74
    "approval_status": "approved",
            
75
    "created": "2024-11-25T12:11:38.292601",
75
    "created": "2024-11-25T12:11:38.292601",
            
76
    "description": "",
76
    "description": "",
            
77
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
77
    "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
78
    "image_url": "",
78
    "image_url": "",
            
79
    "is_organization": true,
79
    "is_organization": true,
            
80
    "name": "no-organization",
80
    "name": "no-organization",
            
81
    "state": "active",
81
    "state": "active",
            
82
    "title": "No Organization",
82
    "title": "No Organization",
            
83
    "type": "organization"
83
    "type": "organization"
            
84
  },
84
  },
            
85
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
85
  "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            
86
  "private": false,
86
  "private": false,
            
87
  "relationships_as_object": [],
87
  "relationships_as_object": [],
            
88
  "relationships_as_subject": [],
88
  "relationships_as_subject": [],
            
t
89
  "resources": [],
t
89
  "resources": [
            
90
    {
            
91
      "cache_last_updated": null,
            
92
      "cache_url": null,
            
93
      "created": "2024-12-02T18:38:42",
            
94
      "data": [
            
95
        "dcterms:title",
            
96
        "dcterms:accessRights",
            
97
        "dcterms:creator",
            
98
        "dcterms:description",
            
99
        "dcterms:issued",
            
100
        "dcterms:language",
            
101
        "dcterms:identifier",
            
102
        "dcat:theme",
            
103
        "dcterms:type",
            
104
        "dcat:keyword",
            
105
        "dcat:landingPage",
            
106
        "dcterms:hasVersion",
            
107
        "dcterms:format",
            
108
        "mls:task",
            
109
        "datacite:isDescribedBy"
            
110
      ],
            
111
      "description": "The json representation of the dataset with its 
            
112
distributions based on DCAT.",
            
113
      "format": "JSON",
            
114
      "hash": "",
            
115
      "id": "9fe09b00-d937-4b2e-826c-540f833e6013",
            
116
      "last_modified": "2024-12-02T18:01:58.235286",
            
117
      "metadata_modified": "2024-12-02T18:01:58.245741",
            
118
      "mimetype": "application/json",
            
119
      "mimetype_inner": null,
            
120
      "name": "Original Metadata",
            
121
      "package_id": "8b69e6ea-d51d-4a11-8054-8e82e1522d9a",
            
122
      "position": 0,
            
123
      "resource_type": null,
            
124
      "size": 828,
            
125
      "state": "active",
            
126
      "url": 
            
127
resource/9fe09b00-d937-4b2e-826c-540f833e6013/download/metadata.json",
            
128
      "url_type": "upload"
            
129
    }
            
130
  ],
            
90
  "services_used_list": "",
131
  "services_used_list": "",
            
91
  "state": "active",
132
  "state": "active",
            
92
  "tags": [
133
  "tags": [
            
93
    {
134
    {
            
94
      "display_name": "CCNet",
135
      "display_name": "CCNet",
            
95
      "id": "8cfd2237-9fd4-4dad-abb4-9ca51b5d3ef3",
136
      "id": "8cfd2237-9fd4-4dad-abb4-9ca51b5d3ef3",
            
96
      "name": "CCNet",
137
      "name": "CCNet",
            
97
      "state": "active",
138
      "state": "active",
            
98
      "vocabulary_id": null
139
      "vocabulary_id": null
            
99
    },
140
    },
            
100
    {
141
    {
            
101
      "display_name": "French Language",
142
      "display_name": "French Language",
            
102
      "id": "b23bb708-4f24-4781-a647-058c0476999b",
143
      "id": "b23bb708-4f24-4781-a647-058c0476999b",
            
103
      "name": "French Language",
144
      "name": "French Language",
            
104
      "state": "active",
145
      "state": "active",
            
105
      "vocabulary_id": null
146
      "vocabulary_id": null
            
106
    },
147
    },
            
107
    {
148
    {
            
108
      "display_name": "Language models",
149
      "display_name": "Language models",
            
109
      "id": "c3d6693e-d010-4c73-a26f-78a05fd8b540",
150
      "id": "c3d6693e-d010-4c73-a26f-78a05fd8b540",
            
110
      "name": "Language models",
151
      "name": "Language models",
            
111
      "state": "active",
152
      "state": "active",
            
112
      "vocabulary_id": null
153
      "vocabulary_id": null
            
113
    },
154
    },
            
114
    {
155
    {
            
115
      "display_name": "Text Data",
156
      "display_name": "Text Data",
            
116
      "id": "a72366d9-3035-43be-8190-608b1c5c787b",
157
      "id": "a72366d9-3035-43be-8190-608b1c5c787b",
            
117
      "name": "Text Data",
158
      "name": "Text Data",
            
118
      "state": "active",
159
      "state": "active",
            
119
      "vocabulary_id": null
160
      "vocabulary_id": null
            
120
    },
161
    },
            
121
    {
162
    {
            
122
      "display_name": "Text datasets",
163
      "display_name": "Text datasets",
            
123
      "id": "3e071e8c-2466-45cc-8622-8dbc7f2e26b8",
164
      "id": "3e071e8c-2466-45cc-8622-8dbc7f2e26b8",
            
124
      "name": "Text datasets",
165
      "name": "Text datasets",
            
125
      "state": "active",
166
      "state": "active",
            
126
      "vocabulary_id": null
167
      "vocabulary_id": null
            
127
    }
168
    }
            
128
  ],
169
  ],
            
129
  "title": "CCNet",
170
  "title": "CCNet",
            
130
  "type": "dataset",
171
  "type": "dataset",
            
131
  "version": ""
172
  "version": ""
            
132
}
173
}