{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001012539,0.00009981728,0.0002706481,0.0008057778,0.0003904164,0.00003431126,0.0003439807,0.0001239277,0.0000611989],"category_scores_gemma":[0.00166312,0.00006250903,0.0001932213,0.002096365,0.0001411277,0.0001286029,0.0000111931,0.000322993,2.394429e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002428283,"about_ca_system_score_gemma":0.000770948,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0105326,"about_ca_topic_score_gemma":0.02312992,"domain_scores_codex":[0.9985432,0.00005674267,0.0005220936,0.0001634588,0.0004120525,0.0003024557],"domain_scores_gemma":[0.9967258,0.001670896,0.0002936107,0.0002560874,0.0008788139,0.0001747762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00320494,0.0003799342,0.2965114,0.0003515988,0.001924961,0.00000684727,0.004537942,0.512275,0.1478757,0.009842727,0.020353,0.00273601],"study_design_scores_gemma":[0.001425727,0.0008639789,0.05661056,0.0002731381,0.0006288919,0.00002009046,0.001966017,0.5963913,0.3269567,0.01353717,0.00111481,0.0002115877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8511347,0.0002502782,0.1465258,0.001037523,0.00002935987,0.0005430654,0.0002071393,0.000004170781,0.0002680699],"genre_scores_gemma":[0.9988532,0.00004154505,0.0006446668,0.00003532458,0.00009589321,0.0001031924,0.00002851628,0.00001311801,0.0001845509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2399008,"threshold_uncertainty_score":0.9960563,"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."}}