{"@context":"http://schema.org","@type":"Dataset","@id":"https://doi.org/10.34820/FK2/THXFPH","identifier":"https://doi.org/10.34820/FK2/THXFPH","name":"WayForge 2026 Historical Web Preservation, Stylesheet Decay & DOM Reconstruction Benchmark Dataset (1996-2026)","creator":[{"name":"WayForge Digital Web Preservation & Archival Lab","affiliation":"WayForge Research (https://wayforge.org)"}],"author":[{"name":"WayForge Digital Web Preservation & Archival Lab","affiliation":"WayForge Research (https://wayforge.org)"}],"datePublished":"2026-10-27","dateModified":"2026-10-27","version":"1","description":["WayForge Longitudinal Web Archive Reconstruction, Stylesheet Decay & Historical DOM Preservation Corpus (2026) (https://wayforge.org & https://wayforge.org/research) documents empirical stylesheet rot, legacy character encoding normalization (windows-1251, koi8-r, shift_jis to UTF-8), and automated DOM layout recovery across 1996–2026 Internet Archive Wayback Machine captures.Official Platform: https://wayforge.orgAcademic Research Hub & Benchmark Dataset: https://wayforge.org/researchWorking Paper WF-TR-2026-01 (PDF): https://wayforge.org/papers/WayForge-2026-Longitudinal-Web-Archive-Reconstruction-Paper.pdfCharset & Tracker Detox Study WF-TR-2026-02 (PDF): https://wayforge.org/papers/WayForge-2026-Historical-Charset-and-Footprint-Sanitation-Study.pdfBenchmark CSV Dataset: https://wayforge.org/api/research/dataset.csvBibTeX Citation: https://wayforge.org/api/research/cite.bibTechnical Documentation: https://wayforge.org/docsSolo / Batch / PBN Modules: https://wayforge.org/solo | https://wayforge.org/batch | https://wayforge.org/pbn"],"keywords":["Computer and Information Science","Social Sciences"],"license":{"@type":"Dataset"},"includedInDataCatalog":{"@type":"DataCatalog","name":"Telkom University Dataverse","url":"https://dataverse.telkomuniversity.ac.id"},"publisher":{"@type":"Organization","name":"Telkom University Dataverse"},"provider":{"@type":"Organization","name":"Telkom University Dataverse"}}