{"id":"W1990304459","doi":"10.1109/jstars.2012.2217940","title":"Evaluating SAR Sea Ice Image Segmentation Using Edge-Preserving Region-Based MRFs","year":2012,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Synthetic aperture radar; Artificial intelligence; Computer science; Image segmentation; Segmentation; Speckle noise; Pattern recognition (psychology); Computer vision; Speckle pattern; Radar imaging; Feature extraction; Remote sensing; Geology; Radar","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":[],"consensus_categories":[],"category_scores_codex":[0.0008429952,0.0001482456,0.0002267247,0.0001905829,0.0003304901,0.00007598865,0.00008962125,0.0001019883,0.00002105052],"category_scores_gemma":[0.0001752783,0.0001340677,0.00004197474,0.0005652813,0.00007283944,0.000366047,0.000007088943,0.0004117271,0.000001271015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003442792,"about_ca_system_score_gemma":0.0002063158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004791415,"about_ca_topic_score_gemma":0.0002422292,"domain_scores_codex":[0.9985114,0.0001184074,0.0005160263,0.0001376834,0.0003731397,0.0003433456],"domain_scores_gemma":[0.9987814,0.0002658929,0.0003865458,0.0001158979,0.0003278761,0.000122363],"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":[0.0001876246,0.00006385482,0.2504457,0.000225899,0.0001034079,0.00004644443,0.002986819,0.1228756,0.0454204,0.00007048787,0.00005729993,0.5775165],"study_design_scores_gemma":[0.0005646975,0.00004891126,0.1593706,0.0001558655,0.00005651871,0.0001325481,0.0005405035,0.83735,0.001068936,0.0004144997,0.0001223556,0.0001745885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9047837,0.0001125966,0.09399711,0.0002636738,0.0003490583,0.0001373428,0.000003412653,0.00001252296,0.0003405424],"genre_scores_gemma":[0.6562856,0.00004910152,0.3430267,0.0001993749,0.0004036729,8.127507e-9,0.00001265109,0.00000607475,0.00001674828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7144744,"threshold_uncertainty_score":0.5467123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0604317506395869,"score_gpt":0.2856795015404351,"score_spread":0.2252477509008483,"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."}}