{"id":"W4415190844","doi":"10.1145/3731599.3767340","title":"Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Preprocessor; Scalability; Sampling (signal processing); Training (meteorology); Entropy (arrow of time); Training set; Scale (ratio); Energy (signal processing)","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":[0.001260151,0.0008555917,0.0008048697,0.0004920355,0.0005713266,0.0008356813,0.001657214,0.0009658147,0.001835942],"category_scores_gemma":[0.008132294,0.0005049849,0.0006959242,0.0006334504,0.0008117596,0.001662245,0.001567267,0.00184832,0.0006392938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006404765,"about_ca_system_score_gemma":0.0009788222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005057752,"about_ca_topic_score_gemma":0.01064192,"domain_scores_codex":[0.9995884,0.0001631575,0.00002574353,0.00008636602,0.00009281518,0.000043548],"domain_scores_gemma":[0.9985245,0.000729879,0.00008143346,0.0004409498,0.0001521589,0.00007112054],"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":[0.0001794627,0.000119639,0.003736319,0.0001190315,0.0000822866,0.0001063318,0.0001010662,0.9064875,0.006271265,0.009380832,0.006888735,0.06652765],"study_design_scores_gemma":[0.00000570996,0.000008906595,0.0001595455,0.000002704151,0.000001803071,0.000009546756,0.000006997683,0.9952192,0.000971213,0.00323862,0.0003729837,0.000002705352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06231171,0.0003351495,0.9298145,0.0006932529,0.00007447927,0.00005577314,0.0006475637,0.004559909,0.001507687],"genre_scores_gemma":[0.6395305,0.0001975372,0.3548486,0.0003711138,0.00007417974,0.0001886514,0.003129093,0.0006739058,0.0009864806],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005057752,"threshold_uncertainty_score":0.01005661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2082254104600204,"score_gpt":0.3240852017145748,"score_spread":0.1158597912545544,"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."}}