{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":2,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/an-internal-cluster-validity-index-based-on","slug":"an-internal-cluster-validity-index-based-on","title":"An Internal Cluster Validity Index Using a Distance-based Separability Measure","date":"2020-09-02","arxiv_id":"2009.01328","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-internal-validity-index-based-on-density","slug":"an-internal-validity-index-based-on-density","title":"An Internal Validity Index Based on Density-Involved Distance","date":"2019-03-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/an-internal-cluster-validity-index-based-on","slug":"an-internal-cluster-validity-index-based-on","title":"An Internal Cluster Validity Index Using a Distance-based Separability Measure","date":"2020-09-02","arxiv_id":"2009.01328","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-internal-validity-index-based-on-density","slug":"an-internal-validity-index-based-on-density","title":"An Internal Validity Index Based on Density-Involved Distance","date":"2019-03-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"3624acd773e1cdd92b0f5a47d7165a2d3ebf572006c131d838abb5ee7b4dfb7b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}