{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000258485,0.0002952091,0.0005372724,0.00007372232,0.00003541896,0.00002876727,0.0008879529,0.0003313269,0.00002216259],"category_scores_gemma":[0.0007258019,0.0002859266,0.00008485412,0.00005175891,0.0000897112,0.000001772421,0.004926553,0.0002364762,0.00001455945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001356738,"about_ca_system_score_gemma":0.00009939674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005374968,"about_ca_topic_score_gemma":0.0001906894,"domain_scores_codex":[0.998322,0.00005444121,0.0004509753,0.0007233549,0.0002115031,0.000237773],"domain_scores_gemma":[0.9970998,0.00003731703,0.0008108169,0.001829011,0.0001638324,0.00005924798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006507799,0.0008646305,0.1591464,0.006095604,0.0033047,0.0000586056,0.0002563388,0.0008985309,0.4271845,0.001410059,0.3890395,0.01109036],"study_design_scores_gemma":[0.002775874,0.0005165099,0.1354527,0.0004580974,0.0007111173,0.00002296096,0.0004961147,0.005493928,0.06515545,0.001387589,0.7852293,0.002300296],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7166921,0.0244405,0.1807542,0.0003522974,0.007361925,0.002493271,0.0641147,0.00005412838,0.003736961],"genre_scores_gemma":[0.9649875,0.004188101,0.0242524,0.0001911168,0.0003371739,0.00001470022,0.004932429,0.00005654245,0.001040048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3961899,"threshold_uncertainty_score":0.9999593,"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."}}