Changes
On December 2, 2024 at 6:20:39 PM UTC,
admin:
-
Changed value of field
doi_date_published
to2024-12-02
in CommonCrawl -
Changed value of field
doi_status
toTrue
in CommonCrawl -
Added resource Original Metadata to CommonCrawl
| f | 1 | { | f | 1 | { |
| 2 | "access_rights": "", | 2 | "access_rights": "", | ||
| 3 | "author": "Hu Xu", | 3 | "author": "Hu Xu", | ||
| 4 | "author_email": "", | 4 | "author_email": "", | ||
| 5 | "citation": [ | 5 | "citation": [ | ||
| 6 | "https://doi.org/10.48550/arXiv.2103.10531", | 6 | "https://doi.org/10.48550/arXiv.2103.10531", | ||
| 7 | "https://doi.org/10.48550/arXiv.2210.05613", | 7 | "https://doi.org/10.48550/arXiv.2210.05613", | ||
| 8 | "https://doi.org/10.48550/arXiv.2310.15552", | 8 | "https://doi.org/10.48550/arXiv.2310.15552", | ||
| 9 | "https://doi.org/10.48550/arXiv.2311.13857" | 9 | "https://doi.org/10.48550/arXiv.2311.13857" | ||
| 10 | ], | 10 | ], | ||
| 11 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 11 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
| 12 | "defined_in": "https://doi.org/10.48550/arXiv.2309.16671", | 12 | "defined_in": "https://doi.org/10.48550/arXiv.2309.16671", | ||
| 13 | "doi": "10.57702/ygkh0gji", | 13 | "doi": "10.57702/ygkh0gji", | ||
| n | 14 | "doi_date_published": null, | n | 14 | "doi_date_published": "2024-12-02", |
| 15 | "doi_publisher": "TIB", | 15 | "doi_publisher": "TIB", | ||
| n | 16 | "doi_status": false, | n | 16 | "doi_status": true, |
| 17 | "domain": "https://service.tib.eu/ldmservice", | 17 | "domain": "https://service.tib.eu/ldmservice", | ||
| 18 | "extra_authors": [ | 18 | "extra_authors": [ | ||
| 19 | { | 19 | { | ||
| 20 | "extra_author": "Saining Xie", | 20 | "extra_author": "Saining Xie", | ||
| 21 | "orcid": "" | 21 | "orcid": "" | ||
| 22 | }, | 22 | }, | ||
| 23 | { | 23 | { | ||
| 24 | "extra_author": "Xiaoqing Ellen Tan", | 24 | "extra_author": "Xiaoqing Ellen Tan", | ||
| 25 | "orcid": "" | 25 | "orcid": "" | ||
| 26 | }, | 26 | }, | ||
| 27 | { | 27 | { | ||
| 28 | "extra_author": "Po-Yao Huang", | 28 | "extra_author": "Po-Yao Huang", | ||
| 29 | "orcid": "" | 29 | "orcid": "" | ||
| 30 | }, | 30 | }, | ||
| 31 | { | 31 | { | ||
| 32 | "extra_author": "Russell Howes", | 32 | "extra_author": "Russell Howes", | ||
| 33 | "orcid": "" | 33 | "orcid": "" | ||
| 34 | }, | 34 | }, | ||
| 35 | { | 35 | { | ||
| 36 | "extra_author": "Vasu Sharma", | 36 | "extra_author": "Vasu Sharma", | ||
| 37 | "orcid": "" | 37 | "orcid": "" | ||
| 38 | }, | 38 | }, | ||
| 39 | { | 39 | { | ||
| 40 | "extra_author": "Shang-Wen Li", | 40 | "extra_author": "Shang-Wen Li", | ||
| 41 | "orcid": "" | 41 | "orcid": "" | ||
| 42 | }, | 42 | }, | ||
| 43 | { | 43 | { | ||
| 44 | "extra_author": "Gargi Ghosh", | 44 | "extra_author": "Gargi Ghosh", | ||
| 45 | "orcid": "" | 45 | "orcid": "" | ||
| 46 | }, | 46 | }, | ||
| 47 | { | 47 | { | ||
| 48 | "extra_author": "Luke Zettlemoyer", | 48 | "extra_author": "Luke Zettlemoyer", | ||
| 49 | "orcid": "" | 49 | "orcid": "" | ||
| 50 | }, | 50 | }, | ||
| 51 | { | 51 | { | ||
| 52 | "extra_author": "Christoph Feichtenhofer", | 52 | "extra_author": "Christoph Feichtenhofer", | ||
| 53 | "orcid": "" | 53 | "orcid": "" | ||
| 54 | } | 54 | } | ||
| 55 | ], | 55 | ], | ||
| 56 | "groups": [ | 56 | "groups": [ | ||
| 57 | { | 57 | { | ||
| 58 | "description": "", | 58 | "description": "", | ||
| 59 | "display_name": "Corpora", | 59 | "display_name": "Corpora", | ||
| 60 | "id": "667794ed-334c-4cf5-b72d-f6aa6878b951", | 60 | "id": "667794ed-334c-4cf5-b72d-f6aa6878b951", | ||
| 61 | "image_display_url": "", | 61 | "image_display_url": "", | ||
| 62 | "name": "corpora", | 62 | "name": "corpora", | ||
| 63 | "title": "Corpora" | 63 | "title": "Corpora" | ||
| 64 | }, | 64 | }, | ||
| 65 | { | 65 | { | ||
| 66 | "description": "", | 66 | "description": "", | ||
| 67 | "display_name": "Data Collection", | 67 | "display_name": "Data Collection", | ||
| 68 | "id": "e5407d18-d3c2-4737-9f55-070f579cca99", | 68 | "id": "e5407d18-d3c2-4737-9f55-070f579cca99", | ||
| 69 | "image_display_url": "", | 69 | "image_display_url": "", | ||
| 70 | "name": "data-collection", | 70 | "name": "data-collection", | ||
| 71 | "title": "Data Collection" | 71 | "title": "Data Collection" | ||
| 72 | }, | 72 | }, | ||
| 73 | { | 73 | { | ||
| 74 | "description": "", | 74 | "description": "", | ||
| 75 | "display_name": "Text Data", | 75 | "display_name": "Text Data", | ||
| 76 | "id": "30d52e93-891a-463b-a577-99a00396f012", | 76 | "id": "30d52e93-891a-463b-a577-99a00396f012", | ||
| 77 | "image_display_url": "", | 77 | "image_display_url": "", | ||
| 78 | "name": "text-data", | 78 | "name": "text-data", | ||
| 79 | "title": "Text Data" | 79 | "title": "Text Data" | ||
| 80 | }, | 80 | }, | ||
| 81 | { | 81 | { | ||
| 82 | "description": "", | 82 | "description": "", | ||
| 83 | "display_name": "Text Pre-training", | 83 | "display_name": "Text Pre-training", | ||
| 84 | "id": "6031e61f-b53c-4812-a65c-89f08254f08c", | 84 | "id": "6031e61f-b53c-4812-a65c-89f08254f08c", | ||
| 85 | "image_display_url": "", | 85 | "image_display_url": "", | ||
| 86 | "name": "text-pre-training", | 86 | "name": "text-pre-training", | ||
| 87 | "title": "Text Pre-training" | 87 | "title": "Text Pre-training" | ||
| 88 | }, | 88 | }, | ||
| 89 | { | 89 | { | ||
| 90 | "description": "", | 90 | "description": "", | ||
| 91 | "display_name": "Web Scraping", | 91 | "display_name": "Web Scraping", | ||
| 92 | "id": "94b6a507-ebba-4c82-a532-8fccffb91dab", | 92 | "id": "94b6a507-ebba-4c82-a532-8fccffb91dab", | ||
| 93 | "image_display_url": "", | 93 | "image_display_url": "", | ||
| 94 | "name": "web-scraping", | 94 | "name": "web-scraping", | ||
| 95 | "title": "Web Scraping" | 95 | "title": "Web Scraping" | ||
| 96 | } | 96 | } | ||
| 97 | ], | 97 | ], | ||
| 98 | "id": "b6df4f21-4506-4b09-b0c8-ee8bf4771a9b", | 98 | "id": "b6df4f21-4506-4b09-b0c8-ee8bf4771a9b", | ||
| 99 | "isopen": false, | 99 | "isopen": false, | ||
| 100 | "landing_page": "https://commoncrawl.org/", | 100 | "landing_page": "https://commoncrawl.org/", | ||
| 101 | "license_title": null, | 101 | "license_title": null, | ||
| 102 | "link_orkg": "", | 102 | "link_orkg": "", | ||
| 103 | "metadata_created": "2024-12-02T18:20:37.491047", | 103 | "metadata_created": "2024-12-02T18:20:37.491047", | ||
| n | 104 | "metadata_modified": "2024-12-02T18:20:37.491053", | n | 104 | "metadata_modified": "2024-12-02T18:20:37.857537", |
| 105 | "name": "commoncrawl", | 105 | "name": "commoncrawl", | ||
| 106 | "notes": "CommonCrawl is a non-profit organization that provides a | 106 | "notes": "CommonCrawl is a non-profit organization that provides a | ||
| 107 | large corpus of web pages for research and development purposes.", | 107 | large corpus of web pages for research and development purposes.", | ||
| n | 108 | "num_resources": 0, | n | 108 | "num_resources": 1, |
| 109 | "num_tags": 10, | 109 | "num_tags": 10, | ||
| 110 | "organization": { | 110 | "organization": { | ||
| 111 | "approval_status": "approved", | 111 | "approval_status": "approved", | ||
| 112 | "created": "2024-11-25T12:11:38.292601", | 112 | "created": "2024-11-25T12:11:38.292601", | ||
| 113 | "description": "", | 113 | "description": "", | ||
| 114 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 114 | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
| 115 | "image_url": "", | 115 | "image_url": "", | ||
| 116 | "is_organization": true, | 116 | "is_organization": true, | ||
| 117 | "name": "no-organization", | 117 | "name": "no-organization", | ||
| 118 | "state": "active", | 118 | "state": "active", | ||
| 119 | "title": "No Organization", | 119 | "title": "No Organization", | ||
| 120 | "type": "organization" | 120 | "type": "organization" | ||
| 121 | }, | 121 | }, | ||
| 122 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | 122 | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | ||
| 123 | "private": false, | 123 | "private": false, | ||
| 124 | "relationships_as_object": [], | 124 | "relationships_as_object": [], | ||
| 125 | "relationships_as_subject": [], | 125 | "relationships_as_subject": [], | ||
| t | 126 | "resources": [], | t | 126 | "resources": [ |
| 127 | { | ||||
| 128 | "cache_last_updated": null, | ||||
| 129 | "cache_url": null, | ||||
| 130 | "created": "2024-12-02T18:38:42", | ||||
| 131 | "data": [ | ||||
| 132 | "dcterms:title", | ||||
| 133 | "dcterms:accessRights", | ||||
| 134 | "dcterms:creator", | ||||
| 135 | "dcterms:description", | ||||
| 136 | "dcterms:issued", | ||||
| 137 | "dcterms:language", | ||||
| 138 | "dcterms:identifier", | ||||
| 139 | "dcat:theme", | ||||
| 140 | "dcterms:type", | ||||
| 141 | "dcat:keyword", | ||||
| 142 | "dcat:landingPage", | ||||
| 143 | "dcterms:hasVersion", | ||||
| 144 | "dcterms:format", | ||||
| 145 | "mls:task", | ||||
| 146 | "datacite:isDescribedBy" | ||||
| 147 | ], | ||||
| 148 | "description": "The json representation of the dataset with its | ||||
| 149 | distributions based on DCAT.", | ||||
| 150 | "format": "JSON", | ||||
| 151 | "hash": "", | ||||
| 152 | "id": "2ae2758d-1f3a-4593-8f8b-77d4ad363d82", | ||||
| 153 | "last_modified": "2024-12-02T18:20:37.848584", | ||||
| 154 | "metadata_modified": "2024-12-02T18:20:37.860215", | ||||
| 155 | "mimetype": "application/json", | ||||
| 156 | "mimetype_inner": null, | ||||
| 157 | "name": "Original Metadata", | ||||
| 158 | "package_id": "b6df4f21-4506-4b09-b0c8-ee8bf4771a9b", | ||||
| 159 | "position": 0, | ||||
| 160 | "resource_type": null, | ||||
| 161 | "size": 1180, | ||||
| 162 | "state": "active", | ||||
| 163 | "url": | ||||
| 164 | resource/2ae2758d-1f3a-4593-8f8b-77d4ad363d82/download/metadata.json", | ||||
| 165 | "url_type": "upload" | ||||
| 166 | } | ||||
| 167 | ], | ||||
| 127 | "services_used_list": "", | 168 | "services_used_list": "", | ||
| 128 | "state": "active", | 169 | "state": "active", | ||
| 129 | "tags": [ | 170 | "tags": [ | ||
| 130 | { | 171 | { | ||
| 131 | "display_name": "Corpora", | 172 | "display_name": "Corpora", | ||
| 132 | "id": "976d8258-2146-448d-9f1f-a595d5a260f8", | 173 | "id": "976d8258-2146-448d-9f1f-a595d5a260f8", | ||
| 133 | "name": "Corpora", | 174 | "name": "Corpora", | ||
| 134 | "state": "active", | 175 | "state": "active", | ||
| 135 | "vocabulary_id": null | 176 | "vocabulary_id": null | ||
| 136 | }, | 177 | }, | ||
| 137 | { | 178 | { | ||
| 138 | "display_name": "Corpus", | 179 | "display_name": "Corpus", | ||
| 139 | "id": "5e434f4b-89f6-489e-9e6e-d2ff6003d493", | 180 | "id": "5e434f4b-89f6-489e-9e6e-d2ff6003d493", | ||
| 140 | "name": "Corpus", | 181 | "name": "Corpus", | ||
| 141 | "state": "active", | 182 | "state": "active", | ||
| 142 | "vocabulary_id": null | 183 | "vocabulary_id": null | ||
| 143 | }, | 184 | }, | ||
| 144 | { | 185 | { | ||
| 145 | "display_name": "Data Collection", | 186 | "display_name": "Data Collection", | ||
| 146 | "id": "7cec52fd-2eb1-4c11-9c4c-400d3278cc29", | 187 | "id": "7cec52fd-2eb1-4c11-9c4c-400d3278cc29", | ||
| 147 | "name": "Data Collection", | 188 | "name": "Data Collection", | ||
| 148 | "state": "active", | 189 | "state": "active", | ||
| 149 | "vocabulary_id": null | 190 | "vocabulary_id": null | ||
| 150 | }, | 191 | }, | ||
| 151 | { | 192 | { | ||
| 152 | "display_name": "Text Data", | 193 | "display_name": "Text Data", | ||
| 153 | "id": "a72366d9-3035-43be-8190-608b1c5c787b", | 194 | "id": "a72366d9-3035-43be-8190-608b1c5c787b", | ||
| 154 | "name": "Text Data", | 195 | "name": "Text Data", | ||
| 155 | "state": "active", | 196 | "state": "active", | ||
| 156 | "vocabulary_id": null | 197 | "vocabulary_id": null | ||
| 157 | }, | 198 | }, | ||
| 158 | { | 199 | { | ||
| 159 | "display_name": "Web Pages", | 200 | "display_name": "Web Pages", | ||
| 160 | "id": "0b80ecb2-15c5-4d0b-ac33-528d883c5a75", | 201 | "id": "0b80ecb2-15c5-4d0b-ac33-528d883c5a75", | ||
| 161 | "name": "Web Pages", | 202 | "name": "Web Pages", | ||
| 162 | "state": "active", | 203 | "state": "active", | ||
| 163 | "vocabulary_id": null | 204 | "vocabulary_id": null | ||
| 164 | }, | 205 | }, | ||
| 165 | { | 206 | { | ||
| 166 | "display_name": "commoncrawl", | 207 | "display_name": "commoncrawl", | ||
| 167 | "id": "8dfa4cff-425f-41f1-81ff-ecb3898172da", | 208 | "id": "8dfa4cff-425f-41f1-81ff-ecb3898172da", | ||
| 168 | "name": "commoncrawl", | 209 | "name": "commoncrawl", | ||
| 169 | "state": "active", | 210 | "state": "active", | ||
| 170 | "vocabulary_id": null | 211 | "vocabulary_id": null | ||
| 171 | }, | 212 | }, | ||
| 172 | { | 213 | { | ||
| 173 | "display_name": "document classification", | 214 | "display_name": "document classification", | ||
| 174 | "id": "a5ed96a5-12e0-4be7-95a6-0df5a2af6fcf", | 215 | "id": "a5ed96a5-12e0-4be7-95a6-0df5a2af6fcf", | ||
| 175 | "name": "document classification", | 216 | "name": "document classification", | ||
| 176 | "state": "active", | 217 | "state": "active", | ||
| 177 | "vocabulary_id": null | 218 | "vocabulary_id": null | ||
| 178 | }, | 219 | }, | ||
| 179 | { | 220 | { | ||
| 180 | "display_name": "text data", | 221 | "display_name": "text data", | ||
| 181 | "id": "71552fca-5e8d-428f-82c0-9d2d0160e73d", | 222 | "id": "71552fca-5e8d-428f-82c0-9d2d0160e73d", | ||
| 182 | "name": "text data", | 223 | "name": "text data", | ||
| 183 | "state": "active", | 224 | "state": "active", | ||
| 184 | "vocabulary_id": null | 225 | "vocabulary_id": null | ||
| 185 | }, | 226 | }, | ||
| 186 | { | 227 | { | ||
| 187 | "display_name": "text pre-training", | 228 | "display_name": "text pre-training", | ||
| 188 | "id": "fb405c0f-9173-4141-a885-7bad31eef1fc", | 229 | "id": "fb405c0f-9173-4141-a885-7bad31eef1fc", | ||
| 189 | "name": "text pre-training", | 230 | "name": "text pre-training", | ||
| 190 | "state": "active", | 231 | "state": "active", | ||
| 191 | "vocabulary_id": null | 232 | "vocabulary_id": null | ||
| 192 | }, | 233 | }, | ||
| 193 | { | 234 | { | ||
| 194 | "display_name": "web scraping", | 235 | "display_name": "web scraping", | ||
| 195 | "id": "de6192c1-ff86-496b-9a9e-634a2fb9b683", | 236 | "id": "de6192c1-ff86-496b-9a9e-634a2fb9b683", | ||
| 196 | "name": "web scraping", | 237 | "name": "web scraping", | ||
| 197 | "state": "active", | 238 | "state": "active", | ||
| 198 | "vocabulary_id": null | 239 | "vocabulary_id": null | ||
| 199 | } | 240 | } | ||
| 200 | ], | 241 | ], | ||
| 201 | "title": "CommonCrawl", | 242 | "title": "CommonCrawl", | ||
| 202 | "type": "dataset", | 243 | "type": "dataset", | ||
| 203 | "version": "" | 244 | "version": "" | ||
| 204 | } | 245 | } |