{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004997237,0.0005485618,0.0004707557,0.0004610667,0.0001485086,0.0004915754,0.0005058844,0.0002397177,0.001499947],"category_scores_gemma":[0.0009213818,0.0004160958,0.0004574932,0.0003533055,0.0002531969,0.0004040402,0.0004619628,0.0004959745,0.0004229225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002906121,"about_ca_system_score_gemma":0.0006290594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001974088,"about_ca_topic_score_gemma":0.003770857,"domain_scores_codex":[0.9998245,0.00002594189,0.000007788877,0.00004886016,0.00007651398,0.00001644141],"domain_scores_gemma":[0.9997076,0.0001245107,0.00003256569,0.00005003361,0.00006613904,0.00001906627],"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":[0.0003125479,0.00007226483,0.001963761,0.000206812,0.000118466,0.0002052309,0.0001718542,0.4027194,0.1062597,0.007886744,0.005254501,0.4748287],"study_design_scores_gemma":[0.0000175285,0.00002945544,0.0006556396,0.000006103312,0.000009319619,0.00007057419,0.00001238778,0.9693466,0.02607986,0.001180621,0.002582481,0.000009377498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008872267,0.00004100304,0.989548,0.00002143933,0.00001374655,0.00002657815,0.0001496901,0.0007836565,0.0005436073],"genre_scores_gemma":[0.10813,0.00008880809,0.8885106,0.00003040874,0.00002316066,0.0000901704,0.00132512,0.0004205659,0.001381006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001974088,"threshold_uncertainty_score":0.005017817,"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."}}