{"id":"W4389625850","doi":"10.5194/egusphere-2023-2648","title":"The AutoICE Challenge","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada; University of Waterloo","funders":"European Space Agency","keywords":"Sea ice; Computer science; Convolutional neural network; Sea ice concentration; Synthetic aperture radar; Remote sensing; Arctic ice pack; Artificial intelligence; Meteorology; Sea ice thickness; Geology; Geography","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":[0.009013564,0.002306449,0.001729518,0.00143883,0.00253719,0.006512922,0.002968611,0.004270939,0.04162222],"category_scores_gemma":[0.01653565,0.0004874539,0.002072993,0.001286146,0.001032191,0.004721913,0.007196755,0.004147355,0.03235904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00142263,"about_ca_system_score_gemma":0.003760386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00638104,"about_ca_topic_score_gemma":0.01570724,"domain_scores_codex":[0.9927639,0.002527795,0.0003071179,0.001688655,0.00177208,0.0009403947],"domain_scores_gemma":[0.9840102,0.004897047,0.0003314146,0.00232968,0.004758202,0.003673526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002818415,0.0001887937,0.0007597198,0.0006588674,0.00005792332,0.0002266479,0.0002129055,0.002634137,0.001279348,0.002097542,0.9533554,0.03824685],"study_design_scores_gemma":[0.0001596956,0.00020828,0.00298768,0.0003361795,0.00003306635,0.0004875199,0.0006820199,0.01474568,0.002009237,0.007271906,0.9709997,0.00007908441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1048012,0.02836117,0.1044899,0.08955967,0.07910183,0.002599188,0.2755589,0.05648432,0.259044],"genre_scores_gemma":[0.1577813,0.004580572,0.07852112,0.01452844,0.009085491,0.002541522,0.512395,0.01034051,0.2102261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04162222,"threshold_uncertainty_score":0.1392402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03546621003412354,"score_gpt":0.2390401718576957,"score_spread":0.2035739618235722,"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."}}