{"id":11812469,"identifier":"DVN/8ZEEJC","persistentUrl":"https://doi.org/10.7910/DVN/8ZEEJC","protocol":"doi","authority":"10.7910","separator":"/","publisher":"Harvard Dataverse","publicationDate":"2025-07-24","storageIdentifier":"s3://10.7910/DVN/8ZEEJC","datasetType":"dataset","datasetVersion":{"id":498970,"datasetId":11812469,"datasetPersistentId":"doi:10.7910/DVN/8ZEEJC","storageIdentifier":"s3://10.7910/DVN/8ZEEJC","versionNumber":2,"versionMinorNumber":1,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","lastUpdateTime":"2025-07-28T22:09:41Z","releaseTime":"2025-07-28T22:09:41Z","createTime":"2025-07-28T21:57:07Z","publicationDate":"2025-07-24","citationDate":"2025-07-24","license":{"name":"CC0 1.0","uri":"http://creativecommons.org/publicdomain/zero/1.0","iconUri":"https://licensebuttons.net/p/zero/1.0/88x31.png","rightsIdentifier":"CC0-1.0","rightsIdentifierScheme":"SPDX","schemeUri":"https://spdx.org/licenses/","languageCode":"en"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Topic_Modeling_Copyright_Infringement_Cases_from_CourtListener"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Tice, Ben"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Washington"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Park, Christine"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Washington"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Park, Christine"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"University of Washington"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"cjpark23@uw.edu"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"Dataset of all copyright infringement cases pulled from CourtListener.\n\nIncludes topic modeling as a a way to create subject tags that can aid in case retrieval."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2025-07-24"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Law"]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationRelationType":{"typeName":"publicationRelationType","multiple":false,"typeClass":"controlledVocabulary","value":"IsSupplementedBy"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"url"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://huggingface.co/spaces/BenTice1996/Topic_Modeling_Copyright_Infringement_Cases_from_CourtListener"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"UI for 4 thousand case data set"},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Tice, Ben"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2025-07-24"}]}},"files":[{"label":"opinions_with_topics.csv","restricted":false,"version":1,"datasetVersionId":498970,"dataFile":{"id":11812470,"persistentId":"","filename":"opinions_with_topics.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":2089569608,"storageIdentifier":"s3://dvn-cloud:1983e452824-f10fb28819d1","rootDataFileId":-1,"md5":"ea5e8d55f127732ddcf7ef78fe3a60c9","checksum":{"type":"MD5","value":"ea5e8d55f127732ddcf7ef78fe3a60c9"},"tabularData":false,"creationDate":"2025-07-24","publicationDate":"2025-07-24","fileAccessRequest":true}},{"description":"smaller UI version\n","label":"opinions_with_topics_ui.csv","restricted":false,"version":1,"datasetVersionId":498970,"dataFile":{"id":11816137,"persistentId":"","filename":"opinions_with_topics_ui.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":586883747,"description":"smaller UI version\n","storageIdentifier":"s3://dvn-cloud:1984355cecb-8f6900cb2321","rootDataFileId":-1,"md5":"5c29c7fc9b05aab821efb182bab113b3","checksum":{"type":"MD5","value":"5c29c7fc9b05aab821efb182bab113b3"},"tabularData":false,"creationDate":"2025-07-25","publicationDate":"2025-07-25","fileAccessRequest":true}}],"citation":"Tice, Ben; Park, Christine, 2025, \"Topic_Modeling_Copyright_Infringement_Cases_from_CourtListener\", https://doi.org/10.7910/DVN/8ZEEJC, Harvard Dataverse, V2"}}