{"id":5698,"identifier":"FK2/O54LWP","persistentUrl":"https://doi.org/10.60507/FK2/O54LWP","protocol":"doi","authority":"10.60507","separator":"/","publisher":"bonndata","publicationDate":"2024-07-15","storageIdentifier":"file://10.60507/FK2/O54LWP","metadataLanguage":"de-DE","datasetType":"dataset","datasetVersion":{"id":368,"datasetId":5698,"datasetPersistentId":"doi:10.60507/FK2/O54LWP","storageIdentifier":"file://10.60507/FK2/O54LWP","versionNumber":2,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionLink":"","lastUpdateTime":"2025-01-14T11:07:50Z","releaseTime":"2025-01-14T11:07:50Z","createTime":"2025-01-13T15:17:32Z","publicationDate":"2024-07-15","citationDate":"2024-07-15","license":{"name":"CC BY 4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://licensebuttons.net/l/by/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Replication data for \"Analyzing the Potency of Pretrained Transformer Models for Automated Program Repair\""},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Leiwig, Maximilian"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn, Lamarr Institute"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0006-5703-5708","expandedvalue":{"personName":"Leiwig, Maximilian","@id":"https://orcid.org/0009-0006-5703-5708","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Swierzy, Ben"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0003-0485-4791","expandedvalue":{"personName":"Swierzy, Ben","@id":"https://orcid.org/0009-0003-0485-4791","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Bungartz, Christian"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn, Lamarr Institute"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0008-0576-8744","expandedvalue":{"personName":"Bungartz, Christian","@id":"https://orcid.org/0009-0008-0576-8744","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Meier, Michael"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn, Fraunhofer FKIE, Lamarr Institute"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0006-8199-5004","expandedvalue":{"personName":"Meier, Michael","@id":"https://orcid.org/0009-0006-8199-5004","scheme":"ORCID","@type":"https://schema.org/Person"}}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Leiwig, Maximilian"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"s6maleiw@uni-bonn.de"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"This repository contains replication data for the paper \"Analyzing the Potency of Pretrained Transformer Models for Automated Program Repair\".<br>\nThe dataset contains commits that indicate a bug fix from 200 repositories on Github.\nScripts for fetching data associated with the commits are available (see Github repository linked under \"Related Material\").\n<hr>\n\nFile descriptions:\n<ul>\n<li><code>repositories.csv</code>: List of repository names with metadata</li>\n<li><code>commits.csv</code>: List of commit identifiers of the 200 repositories with most bug fixing commits</li>\n<li><code>commits_high_watch_count.csv</code>: List of commit identifiers of the 200 repositories with most bug fixing commits with a watch count of at least 50</li>\n</ul>\n\n<hr>\nIcon licensed under CC-BY by xinh.studio"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science"]},{"typeName":"subjectRefinement","multiple":true,"typeClass":"compound","value":[{"subjectRefinementValue":{"typeName":"subjectRefinementValue","multiple":false,"typeClass":"primitive","value":"Computer Science: Software Engineering and Programming Languages [409-02]"}}]},{"typeName":"freeKeyword","multiple":true,"typeClass":"compound","value":[{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Program Repair"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Machine Learning"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Large Language Models"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationRelationType":{"typeName":"publicationRelationType","multiple":false,"typeClass":"controlledVocabulary","value":"IsSupplementTo"},"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"M. Leiwig, B. Swierzy, C. Bungartz and M. Meier, \"Analyzing the Potency of Pretrained Transformer Models for Automated Program Repair,\" 2024 50th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Paris, France, 2024, pp. 72-79, doi: 10.1109/SEAA64295.2024.00020."},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.1109/SEAA64295.2024.00020."},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://doi.org/10.1109/SEAA64295.2024.00020"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"The corresponding paper was be published at SEAA Aug 28 - Aug 30 2024."},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["Not applicable"]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Leiwig, Maximilian"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2024-07-08"},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["quantitative"]},{"typeName":"relatedMaterial","multiple":true,"typeClass":"primitive","value":["Code: https://github.com/Synrom/FixMe"]},{"typeName":"accessToSources","multiple":false,"typeClass":"primitive","value":"Original Sources are Google BigQuery and GitHub"}]}},"files":[{"label":"README.md","restricted":false,"version":1,"datasetVersionId":368,"dataFile":{"id":7925,"persistentId":"doi:10.60507/FK2/O54LWP/SQT1JC","pidURL":"https://doi.org/10.60507/FK2/O54LWP/SQT1JC","filename":"README.md","contentType":"text/markdown","friendlyType":"Markdown Text","filesize":1945,"storageIdentifier":"file://194647d7e1f-26f12a33d2dd","rootDataFileId":5725,"previousDataFileId":5725,"md5":"bd4306963175ff314ccc46d7601a2b35","checksum":{"type":"MD5","value":"bd4306963175ff314ccc46d7601a2b35"},"tabularData":false,"creationDate":"2025-01-14","publicationDate":"2025-01-14","fileAccessRequest":true}},{"label":"commits.csv","restricted":false,"version":1,"datasetVersionId":368,"dataFile":{"id":5723,"persistentId":"doi:10.60507/FK2/O54LWP/WKVPJO","pidURL":"https://doi.org/10.60507/FK2/O54LWP/WKVPJO","filename":"commits.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":6963520,"storageIdentifier":"file://190acc82e1b-9f1cd457adca","rootDataFileId":-1,"md5":"32a7d4bbb62765d708713b2ca8d6f5a8","checksum":{"type":"MD5","value":"32a7d4bbb62765d708713b2ca8d6f5a8"},"tabularData":false,"creationDate":"2024-07-13","publicationDate":"2024-07-15","fileAccessRequest":true}},{"label":"commits_high_watch_count.csv","restricted":false,"version":1,"datasetVersionId":368,"dataFile":{"id":5724,"persistentId":"doi:10.60507/FK2/O54LWP/ASXZU5","pidURL":"https://doi.org/10.60507/FK2/O54LWP/ASXZU5","filename":"commits_high_watch_count.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":1567538,"storageIdentifier":"file://190acc82c62-572eab2f5162","rootDataFileId":-1,"md5":"64524b826cd44b2abf7064b794dbe6fe","checksum":{"type":"MD5","value":"64524b826cd44b2abf7064b794dbe6fe"},"tabularData":false,"creationDate":"2024-07-13","publicationDate":"2024-07-15","fileAccessRequest":true}},{"label":"repositories.csv","restricted":false,"directoryLabel":"public","version":1,"datasetVersionId":368,"dataFile":{"id":5712,"persistentId":"doi:10.60507/FK2/O54LWP/90YM7M","pidURL":"https://doi.org/10.60507/FK2/O54LWP/90YM7M","filename":"repositories.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":3144907,"storageIdentifier":"file://19091b71f92-1ab664bd7d4d","rootDataFileId":-1,"md5":"f578867bd4854a1b228f335aa1b75d26","checksum":{"type":"MD5","value":"f578867bd4854a1b228f335aa1b75d26"},"tabularData":false,"creationDate":"2024-07-08","publicationDate":"2024-07-15","fileAccessRequest":true}}],"citation":"Leiwig, Maximilian; Swierzy, Ben; Bungartz, Christian; Meier, Michael, 2024, \"Replication data for \"Analyzing the Potency of Pretrained Transformer Models for Automated Program Repair\"\", https://doi.org/10.60507/FK2/O54LWP, bonndata, V2"}}