{"id":"W2560103883","doi":"","title":"Semi-Supervised Detection of Extreme Weather Events in Large Climate Datasets","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Autoencoder; Extreme weather; Bounding overwatch; Climate pattern; Convolutional neural network; Machine learning; Data mining; Deep learning; Artificial intelligence; Climate change","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":[0.0002233919,0.00007334932,0.0001198917,0.00006840165,0.0002253803,0.000009622911,0.0002917734,0.00005426875,0.001081737],"category_scores_gemma":[0.00004220492,0.00006747538,0.00004026285,0.0001070252,0.00004542966,0.0003309229,0.00003462863,0.00007459521,0.0001095462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004895799,"about_ca_system_score_gemma":0.000007739472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005643428,"about_ca_topic_score_gemma":0.003633803,"domain_scores_codex":[0.9993654,0.00006783677,0.00010362,0.0002185215,0.00004254172,0.0002020199],"domain_scores_gemma":[0.9994214,0.00005558913,0.00009132176,0.0003512294,0.00001438808,0.00006605151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006830249,0.00003261806,0.9831147,0.000006788549,0.000006848803,0.00001709659,0.00002725356,0.01531347,0.000172514,0.0004663956,0.000002978561,0.0007710527],"study_design_scores_gemma":[0.0005570564,0.00004527188,0.832539,0.000006774367,0.00001032178,3.078823e-7,0.00004485371,0.1639282,0.00003686968,0.002571395,0.0001839161,0.0000760489],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994776,0.00001733933,0.0008639429,0.00001016284,0.00007607781,0.00008878659,0.0002365985,0.00001233692,0.003918784],"genre_scores_gemma":[0.9997019,0.00004281459,0.00002073636,0.00002167745,0.00001320915,3.767139e-8,0.00008175858,0.000001500219,0.0001164344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1505757,"threshold_uncertainty_score":0.9998314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0914682884358318,"score_gpt":0.1971887624375331,"score_spread":0.1057204740017013,"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."}}