Changes

On December 3, 2024 at 9:59:14 AM UTC, admin:

Changed title to RCV1 Dataset (previously RCV1 dataset)

Set author of RCV1 Dataset to Rie Johnson (previously Shlomo E. Chazan)

Updated description of RCV1 Dataset from
The RCV1 dataset is used for predicting categories of newswire stories recently collected by Reuters. Ltd. The RCV1 can be naturally partitioned based on news category and used for federated learning experiments, since readers may only be interested in one or two categories of news and the model training process will mimic the personalized privacy-preserving news recommender system, for which reader history is located on a user’s personal devices.
to
The RCV1 dataset is a corpus of Reuters news articles.

Removed the following tags from RCV1 Dataset

Added the following tags to RCV1 Dataset
- Topic Modeling
- News Articles

Changed value of field defined_in to https://doi.org/10.48550/arXiv.1412.1058 in RCV1 Dataset

Changed value of field extra_authors to [{'extra_author': 'Tong Zhang', 'orcid': ''}] in RCV1 Dataset

Changed value of field citation to [] in RCV1 Dataset

Changed value of field landing_page to https://riejohnson.com/cnn_data.html in RCV1 Dataset

Deleted resource Original Metadata from RCV1 Dataset

              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Shlomo E. Chazan", n 3   "author": "Rie Johnson",
            4   "author_email": "", 4   "author_email": "",
            n 5   "citation": [ n 5   "citation": [],
            6     "https://doi.org/10.48550/arXiv.1606.04838", 
            7     "https://doi.org/10.48550/arXiv.1812.06535" 
            8   ], 
            9   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 10   "defined_in": "https://doi.org/10.48550/arXiv.2101.00052", n 7   "defined_in": "https://doi.org/10.48550/arXiv.1412.1058",
            11   "doi": "10.57702/jffbfebe", 8   "doi": "10.57702/jffbfebe",
            12   "doi_date_published": "2024-12-03", 9   "doi_date_published": "2024-12-03",
            13   "doi_publisher": "TIB", 10   "doi_publisher": "TIB",
            14   "doi_status": true, 11   "doi_status": true,
            15   "domain": "https://service.tib.eu/ldmservice", 12   "domain": "https://service.tib.eu/ldmservice",
            16   "extra_authors": [ 13   "extra_authors": [
            17     { 14     {
            n 18       "extra_author": "Sharon Gannot", n 15       "extra_author": "Tong Zhang",
            19       "orcid": "" 
            20     }, 
            21     { 
            22       "extra_author": "Jacob Goldberger", 
            23       "orcid": "" 16       "orcid": ""
            24     } 17     }
            25   ], 18   ],
            26   "groups": [ 19   "groups": [
            27     { 20     {
            28       "description": "", 21       "description": "",
            n 29       "display_name": "Federated Learning", n 22       "display_name": "Topic Modeling",
            30       "id": "549ea2f0-af79-4ec6-8518-504c49ad892b", 23       "id": "8489cf7c-10d2-41e4-8c26-4be59dc15710",
            31       "image_display_url": "", 24       "image_display_url": "",
            n 32       "name": "federated-learning", n 25       "name": "topic-modeling",
            33       "title": "Federated Learning" 26       "title": "Topic Modeling"
            34     }, 
            35     { 
            36       "description": "", 
            37       "display_name": "Text Classification", 
            38       "id": "0707d099-de73-41dc-85f6-93e4efa6bf14", 
            39       "image_display_url": "", 
            40       "name": "text-classification", 
            41       "title": "Text Classification" 
            42     } 27     }
            43   ], 28   ],
            44   "id": "efc92884-5e64-42b1-a0f9-ea4fa762cf5e", 29   "id": "efc92884-5e64-42b1-a0f9-ea4fa762cf5e",
            45   "isopen": false, 30   "isopen": false,
            n 46   "landing_page": "https://www.cs.cornell.edu/~cst2118/RCV1/", n 31   "landing_page": "https://riejohnson.com/cnn_data.html",
            47   "license_title": null, 32   "license_title": null,
            48   "link_orkg": "", 33   "link_orkg": "",
            49   "metadata_created": "2024-12-03T09:53:56.450659", 34   "metadata_created": "2024-12-03T09:53:56.450659",
            n 50   "metadata_modified": "2024-12-03T09:53:56.806906", n 35   "metadata_modified": "2024-12-03T09:59:13.504750",
            51   "name": "rcv1-dataset", 36   "name": "rcv1-dataset",
            n 52   "notes": "The RCV1 dataset is used for predicting categories of  n 37   "notes": "The RCV1 dataset is a corpus of Reuters news articles.",
            53 newswire stories recently collected by Reuters. Ltd. The RCV1 can be  
            54 naturally partitioned based on news category and used for federated  
            55 learning experiments, since readers may only be interested in one or  
            56 two categories of news and the model training process will mimic the  
            57 personalized privacy-preserving news recommender system, for which  
            58 reader history is located on a user\u2019s personal devices.", 
            59   "num_resources": 1, 38   "num_resources": 0,
            60   "num_tags": 5, 39   "num_tags": 2,
            61   "organization": { 40   "organization": {
            62     "approval_status": "approved", 41     "approval_status": "approved",
            63     "created": "2024-11-25T12:11:38.292601", 42     "created": "2024-11-25T12:11:38.292601",
            64     "description": "", 43     "description": "",
            65     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 44     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            66     "image_url": "", 45     "image_url": "",
            67     "is_organization": true, 46     "is_organization": true,
            68     "name": "no-organization", 47     "name": "no-organization",
            69     "state": "active", 48     "state": "active",
            70     "title": "No Organization", 49     "title": "No Organization",
            71     "type": "organization" 50     "type": "organization"
            72   }, 51   },
            73   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 52   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            74   "private": false, 53   "private": false,
            75   "relationships_as_object": [], 54   "relationships_as_object": [],
            76   "relationships_as_subject": [], 55   "relationships_as_subject": [],
            n 77   "resources": [ n 56   "resources": [],
            78     { 
            79       "cache_last_updated": null, 
            80       "cache_url": null, 
            81       "created": "2024-12-03T10:49:30", 
            82       "data": [ 
            83         "dcterms:title", 
            84         "dcterms:accessRights", 
            85         "dcterms:creator", 
            86         "dcterms:description", 
            87         "dcterms:issued", 
            88         "dcterms:language", 
            89         "dcterms:identifier", 
            90         "dcat:theme", 
            91         "dcterms:type", 
            92         "dcat:keyword", 
            93         "dcat:landingPage", 
            94         "dcterms:hasVersion", 
            95         "dcterms:format", 
            96         "mls:task", 
            97         "datacite:isDescribedBy" 
            98       ], 
            99       "description": "The json representation of the dataset with its  
            100 distributions based on DCAT.", 
            101       "format": "JSON", 
            102       "hash": "", 
            103       "id": "32e09c73-9264-488f-81fb-25d267f15d30", 
            104       "last_modified": "2024-12-03T09:53:56.799713", 
            105       "metadata_modified": "2024-12-03T09:53:56.809731", 
            106       "mimetype": "application/json", 
            107       "mimetype_inner": null, 
            108       "name": "Original Metadata", 
            109       "package_id": "efc92884-5e64-42b1-a0f9-ea4fa762cf5e", 
            110       "position": 0, 
            111       "resource_type": null, 
            112       "size": 1190, 
            113       "state": "active", 
            114       "url":  
            115 resource/32e09c73-9264-488f-81fb-25d267f15d30/download/metadata.json", 
            116       "url_type": "upload" 
            117     } 
            118   ], 
            119   "services_used_list": "", 57   "services_used_list": "",
            120   "state": "active", 58   "state": "active",
            121   "tags": [ 59   "tags": [
            122     { 60     {
            n 123       "display_name": "RCV1", n 61       "display_name": "News Articles",
            124       "id": "80cd6a25-a382-44b8-ab19-787b6ba1a907", 62       "id": "3e313f3f-0961-4610-aa8c-43a6bbab375e",
            125       "name": "RCV1", 63       "name": "News Articles",
            126       "state": "active", 64       "state": "active",
            127       "vocabulary_id": null 65       "vocabulary_id": null
            128     }, 66     },
            129     { 67     {
            n 130       "display_name": "federated learning", n 
            131       "id": "be51f0ba-a6f8-40e4-bd0f-c50ea8cb2ce5", 
            132       "name": "federated learning", 
            133       "state": "active", 
            134       "vocabulary_id": null 
            135     }, 
            136     { 
            137       "display_name": "news categorization", 
            138       "id": "2f79626e-85d3-4c01-b4a8-7db37274741f", 
            139       "name": "news categorization", 
            140       "state": "active", 
            141       "vocabulary_id": null 
            142     }, 
            143     { 
            144       "display_name": "text classification", 
            145       "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d", 
            146       "name": "text classification", 
            147       "state": "active", 
            148       "vocabulary_id": null 
            149     }, 
            150     { 
            151       "display_name": "topics", 68       "display_name": "Topic Modeling",
            152       "id": "ce1d71a6-c057-4584-8957-7a46b02becc4", 69       "id": "59a3495c-23b6-4877-a39d-4d262e67fa3e",
            153       "name": "topics", 70       "name": "Topic Modeling",
            154       "state": "active", 71       "state": "active",
            155       "vocabulary_id": null 72       "vocabulary_id": null
            156     } 73     }
            157   ], 74   ],
            t 158   "title": "RCV1 dataset", t 75   "title": "RCV1 Dataset",
            159   "type": "dataset", 76   "type": "dataset",
            160   "version": "" 77   "version": ""
            161 } 78 }