{"id":"W4366493069","doi":"10.1109/tgrs.2023.3268715","title":"Sea Ice Classification Using Mutually Guided Contexts","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Feature (linguistics); Computer science; Contextual image classification; Context (archaeology); Feature extraction; Pattern recognition (psychology); Artificial intelligence; Pixel; Sea ice; Representation (politics); Remote sensing; Image (mathematics); Geology; Geography; Meteorology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003579142,0.0001344365,0.0001290982,0.0001858369,0.000882253,0.00008778129,0.00009468446,0.00007483653,0.00003917686],"category_scores_gemma":[0.00001406467,0.0001154888,0.00004982526,0.0006795215,0.0002651055,0.0002628907,8.908054e-7,0.0001770487,0.0001064807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001197822,"about_ca_system_score_gemma":0.00008165748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002902253,"about_ca_topic_score_gemma":0.0007181736,"domain_scores_codex":[0.9987612,0.00005674471,0.0002008849,0.0003458005,0.0002839489,0.0003513607],"domain_scores_gemma":[0.9994299,0.0001507261,0.00006412811,0.0001673393,0.00005733758,0.0001305907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001658488,0.000005516569,0.0001664282,0.0000134872,0.000008212955,0.00002186757,0.0005309571,0.006791724,0.001341219,0.000005864797,0.00002003707,0.9910781],"study_design_scores_gemma":[0.0001469681,0.00004704448,0.01612889,0.00005503563,0.0000214736,0.0001298787,0.0008777615,0.9817227,0.0002657284,0.000241673,0.0001992495,0.0001636475],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5877275,0.000007446144,0.4105113,0.0003890437,0.0005900376,0.00009452163,0.00001876823,0.00009574937,0.0005656272],"genre_scores_gemma":[0.9810522,0.0001529361,0.01779948,0.0003564626,0.00004909601,1.476451e-8,0.000008396325,0.000005044968,0.0005764224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9909145,"threshold_uncertainty_score":0.6785666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04044498874239198,"score_gpt":0.2646701037376263,"score_spread":0.2242251149952343,"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."}}