{"url":"/dataset/97-synthetic-datasets","name":"97 synthetic datasets","full_name":null,"description_markdown":"97 synthetic datasets consists of 97 datasets (as illustrated in the figure) and can be used to test graph-based clustering algorithms. \r\n\r\nhttps://github.com/deric/clustering-benchmark","description_withheld":null,"homepage":"https://github.com/deric/clustering-benchmark/tree/master/src/main/resources/datasets/artificial","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/chameleon-2-an-improved-graph-based","title":"Chameleon 2: An Improved Graph-Based Clustering Algorithm","first_author":"Tomas Barton","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[{"name":"Clustering Algorithms Evaluation","url":"/task/clustering-algorithms-evaluation","datasets_with_task":"/datasets/task/clustering-algorithms-evaluation"},{"name":"Graph Clustering","url":"/task/graph-clustering","datasets_with_task":"/datasets/task/graph-clustering"}],"languages":[],"variants":["97 synthetic datasets"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/clustering-algorithms-evaluation-on-97","task":"Clustering Algorithms Evaluation","dataset_variant":"97 synthetic datasets","rows":2,"metrics":["HIT-THE-BEST","Rank difference"],"first_row_in_archive_order":{"model":"CVDD","paper":"/paper/an-internal-validity-index-based-on-density","metrics":{"HIT-THE-BEST":"50","Rank difference":"337"},"code_links":[{"title":"hulianyu/CVDD","url":"https://github.com/hulianyu/CVDD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/an-internal-cluster-validity-index-based-on","title":"An Internal Cluster Validity Index Using a Distance-based Separability Measure","date":"2020-09-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-internal-validity-index-based-on-density","title":"An Internal Validity Index Based on Density-Involved Distance","date":"2019-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}