{"id":"W4388844151","doi":"10.5194/gmd-2023-185","title":"Clustering analysis of very large measurement and model datasets on high performance computing platforms","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Computation; A priori and a posteriori; Parallel computing; Message Passing Interface; Grid; Cluster (spacecraft); Algorithm; Message passing; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001499275,0.000224962,0.0004126516,0.000148732,0.0001626781,0.00003429114,0.0002669613,0.0001258917,0.0000360712],"category_scores_gemma":[0.00004345193,0.0001954818,0.00008490434,0.00026366,0.00005996205,0.00008882029,0.002279518,0.0003194527,0.00002098385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002266582,"about_ca_system_score_gemma":0.00001033294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005622901,"about_ca_topic_score_gemma":0.0001483803,"domain_scores_codex":[0.9979632,0.00001709565,0.0004321088,0.0005333358,0.0007445288,0.000309729],"domain_scores_gemma":[0.9991431,0.00005438401,0.0002388274,0.0004753342,0.00001097491,0.00007744174],"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":[0.00001458512,0.00003505543,0.03145645,0.0001227149,0.0002102322,0.000001009066,0.0003782398,0.9632671,0.00007442744,0.00001103457,0.0001553929,0.004273721],"study_design_scores_gemma":[0.000114666,0.00002718851,0.08701642,0.000171879,0.0001964297,2.07167e-7,0.00007413004,0.9118346,0.0002954387,0.00006216722,0.000008075742,0.0001988104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9493704,0.000007784997,0.04961002,0.00002400018,0.0001876976,0.0001273503,0.0002334576,0.00008370727,0.0003555446],"genre_scores_gemma":[0.9953,0.00002872972,0.004266995,0.00003384482,0.00003512319,0.00000483693,0.0002362016,0.00001844026,0.000075842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05555997,"threshold_uncertainty_score":0.7971515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1000074199870351,"score_gpt":0.2896604514624579,"score_spread":0.1896530314754228,"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."}}