{"id":"W2157290854","doi":"10.1109/tgrs.2010.2102765","title":"Synthesis of Remote Sensing Label Fields Using a Tree-Structured Hierarchical Model","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Jet Propulsion Laboratory","keywords":"Synthetic aperture radar; Computer science; Unavailability; Data mining; Ground truth; Synthetic data; Remote sensing; Tree (set theory); Data modeling; Remote sensing application; Segmentation; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002269256,0.0002691752,0.0003220571,0.0003501117,0.0002948852,0.00004630348,0.0001118395,0.0002171942,0.000002579613],"category_scores_gemma":[0.00003355113,0.0002634653,0.00009590748,0.0004912867,0.0003654906,0.0002170058,0.00000315601,0.0003998034,0.000002399943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007843709,"about_ca_system_score_gemma":0.00005970292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004113696,"about_ca_topic_score_gemma":0.0001464653,"domain_scores_codex":[0.9984569,0.00005919619,0.0004044482,0.0004154371,0.0002630247,0.0004009868],"domain_scores_gemma":[0.9991332,0.0001074366,0.00008552553,0.0004319297,0.00009810008,0.0001438342],"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":[0.00002296211,0.000007546614,7.476462e-8,0.00003851208,0.00001681662,0.000009265234,0.0007967951,0.01720379,0.1712847,0.000001644111,0.000001903448,0.810616],"study_design_scores_gemma":[0.0001341926,0.00002250414,0.0000291971,0.0001928888,0.00005671011,0.0001464165,0.00007801338,0.7596606,0.2389511,0.0005149296,0.000004578793,0.0002089314],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2952985,0.00001564326,0.7035107,0.00003712383,0.0003344189,0.0001043121,0.000005182451,0.0001395654,0.0005545579],"genre_scores_gemma":[0.5557202,0.000046098,0.4441276,0.00002642219,0.00001776229,6.63596e-9,2.3634e-7,0.00002605415,0.00003559089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.810407,"threshold_uncertainty_score":0.9999818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04017186020525507,"score_gpt":0.2447447154909258,"score_spread":0.2045728552856707,"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."}}