{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003850559,0.0001941393,0.0002803575,0.00005361357,0.0005661657,0.0002465486,0.002417396,0.0001525628,0.0003139364],"category_scores_gemma":[0.0001340104,0.000134102,0.00007028613,0.0007413688,0.0001421128,0.000439272,0.0025445,0.0002079948,0.001072744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001339623,"about_ca_system_score_gemma":0.00004227282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005102887,"about_ca_topic_score_gemma":0.00001628077,"domain_scores_codex":[0.9976271,0.0001562511,0.0004488463,0.001137926,0.0002515118,0.0003783054],"domain_scores_gemma":[0.9978326,0.0004692716,0.0001767673,0.001200204,0.00006127919,0.0002599075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001931351,0.007050614,0.3806453,0.000290495,0.0009671375,0.000149463,0.001061178,0.07463625,0.1748983,0.07469854,0.1217869,0.1636227],"study_design_scores_gemma":[0.0004490997,0.0001896639,0.2159008,0.000007463103,0.0001360933,0.000035081,0.00004411914,0.6860693,0.001033576,0.009407019,0.08611543,0.0006123649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01473894,0.0000315497,0.9789736,0.004723992,0.0001189958,0.000585941,0.0002291502,0.000391398,0.0002064793],"genre_scores_gemma":[0.5530399,0.00002992642,0.4425494,0.003090616,0.0005130137,0.0003346821,0.0003532758,0.00001383968,0.00007538201],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.611433,"threshold_uncertainty_score":0.999705,"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."}}