{"id":"W2131400122","doi":"10.1109/lgrs.2009.2035136","title":"IceSynth II: Synthesis of SAR Sea-Ice Imagery Using Region-Based Posterior Sampling","year":2009,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Synthetic aperture radar; Sea ice; Ground truth; Remote sensing; Markov random field; Geology; Sampling (signal processing); Computer science; Radar imaging; Image segmentation; Segmentation; Artificial intelligence; Computer vision; Radar; Climatology","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":[0.0003720418,0.0001937216,0.0002660906,0.0001634131,0.0006454046,0.00007681706,0.0001710467,0.00006687059,0.000007786394],"category_scores_gemma":[0.00009424101,0.0001632918,0.00008104063,0.0003410756,0.0004867855,0.000282493,0.0000110095,0.0001513935,0.000003184021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000114329,"about_ca_system_score_gemma":0.00008666384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004119526,"about_ca_topic_score_gemma":0.00007273428,"domain_scores_codex":[0.9984457,0.00006885298,0.0002875616,0.0004044136,0.0003268644,0.0004666363],"domain_scores_gemma":[0.9990734,0.0003172535,0.0001920145,0.0002337126,0.00004927508,0.0001342713],"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":[0.00008487676,0.00001553654,0.007685785,0.00006281339,0.00001379344,0.0001374348,0.0006032217,0.007252191,0.05528846,0.000001095629,0.00004494284,0.9288099],"study_design_scores_gemma":[0.0002111059,0.0001329324,0.05081806,0.0006121911,0.00008017698,0.0004067953,0.0003487925,0.9428501,0.00378078,0.0001015539,0.0001685481,0.0004889856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9310215,0.00003600595,0.06486787,0.003491664,0.000358298,0.00008807568,0.00001217631,0.00003373247,0.00009075435],"genre_scores_gemma":[0.900276,0.00002372103,0.09364472,0.005934624,0.0001005321,2.671291e-9,0.000003778714,0.000004258983,0.00001238067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9355979,"threshold_uncertainty_score":0.6658844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02032353531902342,"score_gpt":0.2255936296966567,"score_spread":0.2052700943776332,"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."}}