{"id":"W4367040796","doi":"10.1016/j.chemolab.2023.104841","title":"Exploring the scores: Procrustes analysis for comprehensive exploration of multivariate data","year":2023,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Data mining; Overfitting; Principal component analysis; Procrustes analysis; Cluster analysis; Hierarchical clustering; Projection pursuit; Preprocessor; Projection (relational algebra); Multivariate statistics; Artificial intelligence; Pattern recognition (psychology); Exploratory data analysis; Visualization; Machine learning; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005545564,0.0002246713,0.0005605204,0.001275685,0.0001944966,0.0001370216,0.0005845394,0.00008507028,0.00001756191],"category_scores_gemma":[0.00101996,0.0001664918,0.0001110423,0.01292037,0.0001024555,0.0005391974,0.0002299372,0.0001351607,0.000007604107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000529324,"about_ca_system_score_gemma":0.00005498263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009963799,"about_ca_topic_score_gemma":0.000004796228,"domain_scores_codex":[0.9981765,0.00002953956,0.0006183017,0.0005115565,0.0003707765,0.0002932826],"domain_scores_gemma":[0.9969218,0.001040492,0.0003787705,0.0008892504,0.0006765442,0.00009317623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007789221,0.001736511,0.1822809,0.02456768,0.04044396,0.0000375431,0.01419052,0.03821317,0.6237909,0.0240787,0.02771426,0.02216684],"study_design_scores_gemma":[0.0008404435,0.0001907261,0.002303487,0.0001689216,0.003713963,0.000001709342,0.03226003,0.1757364,0.7200911,0.00008984284,0.06371059,0.0008928057],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9400114,0.01280836,0.04363333,0.0001459331,0.0005530515,0.0007324432,0.0014248,0.000348034,0.0003426827],"genre_scores_gemma":[0.9955875,0.003017381,0.0001659796,0.000017196,0.0001748127,0.000203814,0.0004919628,0.00002992944,0.0003114132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1799775,"threshold_uncertainty_score":0.6789339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3537586377516224,"score_gpt":0.363730012677846,"score_spread":0.009971374926223686,"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."}}