{"id":"W4401090911","doi":"10.1080/03610918.2024.2378149","title":"On the prediction of rare events when sampling from large data","year":2024,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Covariate; Sampling (signal processing); Stratified sampling; Logistic regression; Sampling design; Simple random sample; Range (aeronautics); Mathematics; Offset (computer science); Importance sampling; Computer science; Sample size determination; Sample (material); Stratum; Data mining; Econometrics; Monte Carlo method; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004459991,0.00007200723,0.00008177131,0.00005012329,0.0001352022,0.00004366836,0.0003628305,0.00003660451,0.0001122341],"category_scores_gemma":[0.0002527338,0.0000621889,0.000008847723,0.0001802498,0.00005879369,0.0001911001,0.0003507377,0.0001310861,0.00004192595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007147795,"about_ca_system_score_gemma":0.000009806643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000277395,"about_ca_topic_score_gemma":0.0002250342,"domain_scores_codex":[0.9990239,0.000232917,0.0002918208,0.0001931413,0.000184547,0.00007364102],"domain_scores_gemma":[0.9960541,0.003112602,0.00008137733,0.0007168803,0.00001565284,0.00001941255],"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":[0.00003876593,0.0003614771,0.04584078,0.0001001253,0.00006548378,0.000001471751,0.006968623,0.6801193,0.0002311537,0.04373096,0.005497081,0.2170448],"study_design_scores_gemma":[0.0001371982,0.00001803585,0.05848643,0.00009511805,0.00001183559,2.34303e-7,0.00006931167,0.9077535,0.000002166749,0.03176526,0.001615799,0.00004508036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1322572,0.0002057469,0.8643821,0.0003116749,0.0001520757,0.0003856794,0.001884229,0.00004463497,0.0003766351],"genre_scores_gemma":[0.9810742,0.00003138172,0.01696155,0.00004563691,0.00001046666,0.00001246645,0.001840559,0.000009725444,0.00001403394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.848817,"threshold_uncertainty_score":0.253599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1392180610278192,"score_gpt":0.3930839989121049,"score_spread":0.2538659378842858,"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."}}