{"id":"W2110190618","doi":"10.1139/x08-099","title":"On the selection of samples for multivariate regression analysis: application to near-infrared (NIR) calibration models for the prediction of pulp yield in <i>Eucalyptus nitens</i>","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Eucalyptus nitens; Calibration; Cross-validation; Model selection; Selection (genetic algorithm); Mathematics; Near-infrared spectroscopy; Computer science; Statistics; Artificial intelligence; Eucalyptus; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.006511502,0.000960088,0.000856231,0.0006476183,0.0002719194,0.0006058632,0.0006241014,0.0006257414,0.0004085859],"category_scores_gemma":[0.01501445,0.0003402973,0.0008188788,0.0005625595,0.0004010515,0.0005480223,0.000520432,0.0005962503,0.0001936939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000387451,"about_ca_system_score_gemma":0.0006892788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002363064,"about_ca_topic_score_gemma":0.003679715,"domain_scores_codex":[0.9964792,0.00208724,0.0002048278,0.00035617,0.0007972589,0.00007526611],"domain_scores_gemma":[0.9895235,0.008702812,0.0005153614,0.0004648959,0.0007356911,0.00005778612],"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":[0.003170952,0.001763203,0.05563719,0.0005814726,0.0004094524,0.0001926622,0.0003600048,0.3007841,0.2340303,0.0009531617,0.0004858752,0.4016315],"study_design_scores_gemma":[0.0001900014,0.003060715,0.04362421,0.00003277901,0.0003304875,0.0001869305,0.0001208637,0.700459,0.249694,0.0007058944,0.001477657,0.0001175014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.825333,0.0004366856,0.1728674,0.0000800959,0.00001556135,0.0002619308,0.0001615301,0.0003626637,0.0004810836],"genre_scores_gemma":[0.7202703,0.0002422743,0.2781872,0.00005087039,0.000008055207,0.0003231675,0.0004774829,0.00004308048,0.0003975322],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006511502,"threshold_uncertainty_score":0.03443646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1016796191663413,"score_gpt":0.3395049496663587,"score_spread":0.2378253305000174,"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."}}