{"id":"W3010960300","doi":"10.1002/eap.2123","title":"Ecological prediction at macroscales using big data: Does sampling design matter?","year":2020,"lang":"en","type":"article","venue":"Ecological Applications","topic":"Data Analysis with R","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Cégep Marie-Victorin","funders":"National Institute of Food and Agriculture; Directorate for Biological Sciences","keywords":"Sampling (signal processing); Ecology; Sampling design; Big data; Environmental science; Geography; Computer science; Biology; Data mining; Population; Sociology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09489474,0.0007631374,0.0008154033,0.0006570707,0.0006682522,0.001674635,0.001874517,0.001126218,0.0007019928],"category_scores_gemma":[0.1910985,0.0006355591,0.001100072,0.001350181,0.001746065,0.002680168,0.001257962,0.001003696,0.0002136153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008762543,"about_ca_system_score_gemma":0.001359989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007337532,"about_ca_topic_score_gemma":0.008465504,"domain_scores_codex":[0.9507272,0.04339894,0.001501021,0.002344665,0.001665877,0.0003623272],"domain_scores_gemma":[0.7516398,0.2070763,0.01137752,0.02323024,0.005678443,0.0009977465],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001278502,0.0003581239,0.7477549,0.0003941324,0.002400031,0.0001612228,0.0009947364,0.173299,0.002998666,0.004865757,0.00235525,0.06313976],"study_design_scores_gemma":[0.0003872569,0.0009725199,0.1811019,0.0002789887,0.0007310526,0.0001836863,0.000863361,0.7798408,0.008043684,0.02373348,0.0037183,0.000144899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6668044,0.0006472202,0.326699,0.001765761,0.000153106,0.0007605358,0.001160455,0.0003837252,0.001625749],"genre_scores_gemma":[0.9576917,0.0001110083,0.04074991,0.0002851609,0.00003683694,0.0004119846,0.0005689298,0.00003933662,0.0001051539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9051052,"threshold_uncertainty_score":0.5018574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.204191952903336,"score_gpt":0.319121722104141,"score_spread":0.1149297692008051,"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."}}