{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01218945,0.0007708586,0.001143001,0.001595362,0.0007659292,0.002313136,0.001302742,0.001501852,0.001796216],"category_scores_gemma":[0.05636469,0.0005091509,0.001086713,0.001597892,0.002835513,0.002405751,0.001865179,0.003026092,0.0002743168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163636,"about_ca_system_score_gemma":0.00120683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003231236,"about_ca_topic_score_gemma":0.002832581,"domain_scores_codex":[0.996155,0.002778938,0.0001286705,0.0003844881,0.0004711423,0.0000817687],"domain_scores_gemma":[0.951771,0.04034131,0.002431563,0.00303279,0.001974423,0.0004488626],"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":[0.0001103502,0.0001002295,0.01019152,0.0001852483,0.0001743928,0.0001120683,0.0002746276,0.891888,0.003014113,0.06858783,0.002038765,0.02332279],"study_design_scores_gemma":[0.00001186215,0.00001237431,0.0009329162,0.00001795067,0.00001049149,0.00001673309,0.00002482343,0.9375203,0.0004938664,0.06053527,0.0004102632,0.00001319405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.133798,0.0004923172,0.8608627,0.002280016,0.00008276782,0.00006229104,0.0005145926,0.0005619389,0.001345314],"genre_scores_gemma":[0.7756858,0.0003979455,0.2215307,0.0004607312,0.00009511533,0.0001938331,0.0007653822,0.0001664452,0.0007041003],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01218945,"threshold_uncertainty_score":0.06446475,"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."}}