{"id":18730,"identifier":"FK2/THXFPH","persistentUrl":"https://doi.org/10.34820/FK2/THXFPH","protocol":"doi","authority":"10.34820","publisher":"Telkom University Dataverse","publicationDate":"2026-10-27","storageIdentifier":"file://10.34820/FK2/THXFPH","datasetVersion":{"id":1173,"datasetId":18730,"datasetPersistentId":"doi:10.34820/FK2/THXFPH","storageIdentifier":"file://10.34820/FK2/THXFPH","versionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","lastUpdateTime":"2026-10-27T03:26:40Z","releaseTime":"2026-10-27T03:26:40Z","createTime":"2026-10-27T03:26:36Z","license":"NONE","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"WayForge 2026 Historical Web Preservation, Stylesheet Decay & DOM Reconstruction Benchmark Dataset (1996-2026)"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"WayForge Digital Web Preservation & Archival Lab"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"WayForge Research (https://wayforge.org)"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"WayForge Research Team"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"support@wayforge.org"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"<p><strong>WayForge Longitudinal Web Archive Reconstruction, Stylesheet Decay &amp; Historical DOM Preservation Corpus (2026)</strong> (<a href=\"https://wayforge.org\">https://wayforge.org</a> &amp; <a href=\"https://wayforge.org/research\">https://wayforge.org/research</a>) documents empirical stylesheet rot, legacy character encoding normalization (<code>windows-1251</code>, <code>koi8-r</code>, <code>shift_jis</code> to <code>UTF-8</code>), and automated DOM layout recovery across 1996–2026 Internet Archive Wayback Machine captures.</p><ul><li>Official Platform: <a href=\"https://wayforge.org\">https://wayforge.org</a></li><li>Academic Research Hub &amp; Benchmark Dataset: <a href=\"https://wayforge.org/research\">https://wayforge.org/research</a></li><li>Working Paper WF-TR-2026-01 (PDF): <a href=\"https://wayforge.org/papers/WayForge-2026-Longitudinal-Web-Archive-Reconstruction-Paper.pdf\">https://wayforge.org/papers/WayForge-2026-Longitudinal-Web-Archive-Reconstruction-Paper.pdf</a></li><li>Charset &amp; Tracker Detox Study WF-TR-2026-02 (PDF): <a href=\"https://wayforge.org/papers/WayForge-2026-Historical-Charset-and-Footprint-Sanitation-Study.pdf\">https://wayforge.org/papers/WayForge-2026-Historical-Charset-and-Footprint-Sanitation-Study.pdf</a></li><li>Benchmark CSV Dataset: <a href=\"https://wayforge.org/api/research/dataset.csv\">https://wayforge.org/api/research/dataset.csv</a></li><li>BibTeX Citation: <a href=\"https://wayforge.org/api/research/cite.bib\">https://wayforge.org/api/research/cite.bib</a></li><li>Technical Documentation: <a href=\"https://wayforge.org/docs\">https://wayforge.org/docs</a></li><li>Solo / Batch / PBN Modules: <a href=\"https://wayforge.org/solo\">https://wayforge.org/solo</a> | <a href=\"https://wayforge.org/batch\">https://wayforge.org/batch</a> | <a href=\"https://wayforge.org/pbn\">https://wayforge.org/pbn</a></li></ul>"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science","Social Sciences"]}]}},"files":[],"citation":"WayForge Digital Web Preservation & Archival Lab, 2026, \"WayForge 2026 Historical Web Preservation, Stylesheet Decay & DOM Reconstruction Benchmark Dataset (1996-2026)\", https://doi.org/10.34820/FK2/THXFPH, Telkom University Dataverse, V1"}}