{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005540256,0.0003765612,0.000378215,0.0002648865,0.00008414228,0.001381856,0.001748901,0.0003981082,0.00005154054],"category_scores_gemma":[0.0002915827,0.0003402086,0.0001890654,0.0003422749,0.00006555476,0.0002453393,0.02629566,0.002335288,0.001204657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003210862,"about_ca_system_score_gemma":0.0009052492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007681669,"about_ca_topic_score_gemma":0.00002037342,"domain_scores_codex":[0.9964511,0.0001175541,0.000398608,0.001390881,0.0009615847,0.0006802995],"domain_scores_gemma":[0.9974154,0.0002841028,0.00008190228,0.001771168,0.0001767959,0.0002706783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001349402,0.000550583,0.000004911688,0.003245114,0.0006474821,0.006705147,0.003002314,0.02781185,0.003052195,0.4072348,0.08671378,0.4608969],"study_design_scores_gemma":[0.0001707411,0.00007920876,0.000003225899,0.0001275719,0.00001114396,0.0001874594,0.00001236426,0.8471207,0.0009178377,0.1198105,0.03109957,0.0004596646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001347286,0.0001453773,0.9532315,0.006005391,0.00978237,0.0004395423,0.000004751224,0.001327558,0.0289288],"genre_scores_gemma":[0.0268653,0.00004180022,0.9544671,0.0001871244,0.002491548,0.0002030281,0.000006517573,0.00007227909,0.01566535],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8193089,"threshold_uncertainty_score":0.9999664,"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."}}