{"id":"W2073994361","doi":"10.1039/c0an00345j","title":"Detecting influential observations by cluster analysis and Monte Carlo cross-validation","year":2010,"lang":"en","type":"article","venue":"The Analyst","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Principal component analysis; Monte Carlo method; Partial least squares regression; Computer science; Cross-validation; Component (thermodynamics); Cluster (spacecraft); Series (stratigraphy); Sample (material); Data mining; Statistics; Artificial intelligence; Mathematics; Machine learning; Chemistry; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002495443,0.0001420218,0.000232673,0.0001743078,0.0004156287,0.0002411881,0.0002496856,0.0001115182,0.0005988465],"category_scores_gemma":[0.0001653826,0.0001067481,0.0001786261,0.001512541,0.0001207571,0.0001825105,0.00007835724,0.0003191528,0.00000936425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002277434,"about_ca_system_score_gemma":0.00001364379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001609815,"about_ca_topic_score_gemma":0.0009886017,"domain_scores_codex":[0.9990194,0.00001889623,0.000282187,0.0002633087,0.0002112541,0.000204958],"domain_scores_gemma":[0.9990318,0.0001513222,0.0001759157,0.0004640946,0.0001100287,0.00006685538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001693819,0.00003253305,0.5081636,0.00001286637,0.001614432,7.120489e-7,0.0002259862,0.0006778912,0.4884114,0.00003073022,0.0003795264,0.0004333462],"study_design_scores_gemma":[0.0006618496,0.00001318955,0.08503698,0.000004136353,0.009524231,0.000007290045,0.0005525152,0.01943272,0.8800468,0.0001564085,0.004115807,0.0004481078],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972049,0.0001436353,0.001205633,0.000275855,0.00002608562,0.00002809924,0.00002752279,0.00005207196,0.001036191],"genre_scores_gemma":[0.9965237,0.00002062106,0.0002181325,0.0001452793,0.0001316557,0.00001062968,0.00004099577,0.00001217827,0.002896751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4231266,"threshold_uncertainty_score":0.655695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01336330654662731,"score_gpt":0.2878486748633483,"score_spread":0.2744853683167209,"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."}}