{"id":"W2910244130","doi":"10.1093/biostatistics/kxz001","title":"Are clusterings of multiple data views independent?","year":2019,"lang":"en","type":"preprint","venue":"Biostatistics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Spurious relationship; Data type; Computer science; Data set; Set (abstract data type); Exploit; Data mining; Data science; Information retrieval; Psychology; Machine learning; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1341361,0.002007551,0.004328854,0.004024855,0.003702585,0.008917959,0.00685137,0.005201365,0.00515091],"category_scores_gemma":[0.3905187,0.002293793,0.008272395,0.00463935,0.01434163,0.01122335,0.007104823,0.008407049,0.001954948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002970662,"about_ca_system_score_gemma":0.002680604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004820782,"about_ca_topic_score_gemma":0.002851199,"domain_scores_codex":[0.8185756,0.08788162,0.009999094,0.05761892,0.021597,0.004327735],"domain_scores_gemma":[0.4119352,0.3928586,0.05359903,0.1138124,0.02271258,0.005082313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.006179141,0.001037566,0.6942118,0.001431746,0.01598688,0.001749068,0.01175507,0.02229265,0.006070089,0.09624461,0.01115047,0.131891],"study_design_scores_gemma":[0.001114012,0.001136169,0.4661829,0.0005458597,0.002419825,0.002552311,0.004582805,0.2141037,0.00676813,0.2892943,0.010608,0.00069204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4130882,0.001719219,0.5590969,0.00692015,0.0007669756,0.001739281,0.00401095,0.0009148878,0.01174352],"genre_scores_gemma":[0.9288039,0.0003436274,0.06170476,0.001343349,0.0005114168,0.0008217942,0.004666057,0.0003278569,0.001477409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1341361,"threshold_uncertainty_score":0.7093877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07597877536538193,"score_gpt":0.3191912477251362,"score_spread":0.2432124723597542,"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."}}