{"id":"W4392895711","doi":"10.1101/2024.03.15.585297","title":"Interpretable and predictive models based on high-dimensional data in ecology and evolution","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data Analysis with R","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"University of Wyoming; National Science Foundation","keywords":"Overfitting; Generalizability theory; Machine learning; Artificial intelligence; Computer science; Predictive modelling; Sample (material); Variable (mathematics); Sample size determination; Process (computing); Feature selection; Model selection; Sampling (signal processing); Selection (genetic algorithm); Ecology; Data mining; Statistics; Mathematics; Artificial neural network; Biology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00110115,0.0004235147,0.0005358543,0.0007468661,0.00008056323,0.0003997035,0.001437143,0.0003654223,0.000005448515],"category_scores_gemma":[0.0001745366,0.0004286534,0.00003780116,0.0006253896,0.0001382087,0.0006462679,0.006110948,0.0008671773,0.00001823299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003322836,"about_ca_system_score_gemma":0.0007035704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001874629,"about_ca_topic_score_gemma":0.00003000311,"domain_scores_codex":[0.9964355,0.000213149,0.0004414541,0.002087011,0.0004089087,0.0004139907],"domain_scores_gemma":[0.9965549,0.000174238,0.0001972282,0.002716633,0.0001652212,0.000191768],"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":[0.00105638,0.003494761,0.1146682,0.005207958,0.003339721,0.002769549,0.0002731365,0.5462127,0.1120972,0.1959123,0.01482438,0.0001436764],"study_design_scores_gemma":[0.0003112698,0.0000720782,0.06508355,0.0004391657,0.00008616522,2.750735e-8,5.006953e-7,0.9326121,0.0006460444,0.0003390184,0.00004122248,0.0003689233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7010191,0.001965252,0.2900665,0.001403471,0.001772655,0.0009714658,0.002270553,0.0005115017,0.00001947226],"genre_scores_gemma":[0.9802404,0.00004111854,0.01924592,0.000266578,0.00008100112,0.00007977051,0.000003940006,0.00003900748,0.000002276526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3863993,"threshold_uncertainty_score":0.9998165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01380212829487882,"score_gpt":0.2197321022657618,"score_spread":0.205929973970883,"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."}}