{"id":"W3203762460","doi":"","title":"Seasonal Sea Ice Presence Forecasting of Hudson Bay using Seq2Seq Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Bay; Sea ice; Oceanography; Climatology; Environmental science; Meteorology; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003756148,0.0001745231,0.0002054081,0.0000909842,0.0002615442,0.00009977255,0.0002826542,0.00006925438,0.005817318],"category_scores_gemma":[0.0008376993,0.0001674902,0.00008941226,0.000184241,0.00008587076,0.0002634811,0.00006237521,0.0007286984,0.00004561711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001806636,"about_ca_system_score_gemma":0.0001926865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001100959,"about_ca_topic_score_gemma":0.0003785456,"domain_scores_codex":[0.9982625,0.0002190466,0.0002967506,0.0003436773,0.0005942205,0.0002837773],"domain_scores_gemma":[0.9987993,0.0004149634,0.0002546569,0.0001036267,0.0003303483,0.0000971408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006326474,0.00001949225,0.7425507,0.00002454403,0.00004705757,0.00006501636,0.0003431597,0.2251596,0.0004007726,0.002012659,0.000004067369,0.02930972],"study_design_scores_gemma":[0.0002420547,0.00009523123,0.03351707,0.0001863507,0.00001565045,0.0001065999,0.0007806517,0.9633825,0.000140569,0.0004674645,0.0008905978,0.0001751955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9497342,0.00007520532,0.008238931,0.0006046908,0.0004780696,0.00006571844,0.00005724367,0.00004957577,0.04069641],"genre_scores_gemma":[0.992658,0.00006382078,0.005004203,0.0001115532,0.0001597226,4.754384e-7,0.0003461339,0.000008305216,0.001647747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.738223,"threshold_uncertainty_score":0.9950915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05208139374302485,"score_gpt":0.2776881007093523,"score_spread":0.2256067069663275,"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."}}