{"url":"/dataset/dejan-synthetic-taxonomy-dataset","name":"DEJAN Synthetic Taxonomy Dataset","full_name":null,"description_markdown":"This dataset contains synthetic text data generated to train models for text generation. The data is created using a large language model (LLM), specifically the GEMMA-2-9B-IT model, and is designed to encompass a diverse range of scenarios and writing styles.","description_withheld":null,"homepage":"https://dejan.ai/","introduced_date":"2024-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/relationships-in-large-scale-graph-computing","title":"Relationships in Large-Scale Graph Computing","first_author":"Dan Petrovic","url":null},"license":{"name":"LInk Attribution","url":"https://dejanmarketing.com/link-attribution/"},"modalities":[],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DEJAN Synthetic Taxonomy Dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}