{"id":"W4392136634","doi":"10.31234/osf.io/fq6e9","title":"Ensemble clustering: A practical tutorial","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Cluster analysis; Computer science; Consensus clustering; Data mining; Ensemble learning; Machine learning; Clustering high-dimensional data; CURE data clustering algorithm; Correlation clustering; Robustness (evolution); Stability (learning theory); Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002069177,0.002394442,0.001258548,0.002198402,0.0008821426,0.002376917,0.001930673,0.0019657,0.04171675],"category_scores_gemma":[0.006206023,0.001097345,0.002008713,0.003061156,0.0007032453,0.003250048,0.001915836,0.003824295,0.03133716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000909043,"about_ca_system_score_gemma":0.0009558079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002083407,"about_ca_topic_score_gemma":0.003039962,"domain_scores_codex":[0.9990133,0.0003334445,0.0000665822,0.0002195431,0.0003194282,0.00004771407],"domain_scores_gemma":[0.998154,0.001053325,0.00006769548,0.0001903277,0.0004339559,0.000100638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004724104,0.0001142493,0.0004960999,0.00104675,0.0001187939,0.0003421064,0.0002516166,0.02151159,0.002009524,0.09404109,0.4230472,0.4569738],"study_design_scores_gemma":[0.000016804,0.00005527127,0.0005946945,0.000368103,0.00002745028,0.000820453,0.0000774744,0.038137,0.0009045185,0.1443734,0.8145478,0.00007693881],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007701771,0.02304083,0.9374545,0.003136025,0.003317555,0.0002405839,0.001172602,0.005512676,0.02535498],"genre_scores_gemma":[0.01255252,0.04460588,0.8706423,0.0030993,0.007231402,0.001007751,0.003943175,0.003362547,0.05355522],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04171675,"threshold_uncertainty_score":0.1395565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06216207200740068,"score_gpt":0.3888206271657487,"score_spread":0.326658555158348,"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."}}