{"id":"W2913760405","doi":"10.48550/arxiv.1901.11040","title":"The Wilderness Area Data Set: Adapting the Covertype data set for unsupervised learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Set (abstract data type); Data set; Cluster analysis; Data stream mining; Context (archaeology); Unsupervised learning; USable; Benchmark (surveying); Data mining; Data stream; Machine learning; Process (computing); Artificial intelligence; Geography; World Wide Web; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002111866,0.0004374191,0.0003860827,0.0001109379,0.0008410431,0.0008136458,0.0279727,0.0002688468,0.000007513069],"category_scores_gemma":[0.0006268504,0.0003302828,0.0001059149,0.0004842756,0.0002082971,0.001341113,0.03909281,0.001066155,0.00004304933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001210598,"about_ca_system_score_gemma":0.0004908976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005134242,"about_ca_topic_score_gemma":0.0001787787,"domain_scores_codex":[0.9962767,0.0003782418,0.0003038208,0.002241602,0.0002118111,0.0005878061],"domain_scores_gemma":[0.9843931,0.00172838,0.0005055827,0.01308323,0.0001910604,0.00009861423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006010651,0.0003226747,0.02324538,0.0008885568,0.002293021,0.0004415481,0.003703529,0.2328553,0.0001202025,0.2560165,0.3986644,0.08084793],"study_design_scores_gemma":[0.0002963706,0.00005116957,0.0001664887,0.000165855,0.0001112517,0.000006370179,0.0003502229,0.915938,0.00002603822,0.004971049,0.07748474,0.0004324152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01121252,0.0001788633,0.9827934,0.0007135109,0.0007584505,0.001095451,0.001646077,0.0006807533,0.0009209628],"genre_scores_gemma":[0.9842482,0.0005141142,0.009130308,0.0001686418,0.0001475372,0.000004524508,0.003857342,0.00005839339,0.001870984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9736631,"threshold_uncertainty_score":0.9999149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3154898749161229,"score_gpt":0.2551777202509075,"score_spread":0.06031215466521539,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}