{"id":"W2943153115","doi":"10.3390/rs11091017","title":"Topology-Aware Road Network Extraction via Multi-Supervised Generative Adversarial Networks","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Terrain; Adversarial system; Topology (electrical circuits); Completeness (order theory); Network topology; Artificial intelligence; Generative adversarial network; Shadow (psychology); Quality (philosophy); Data mining; Machine learning; Deep learning; Computer network; Geography; Mathematics","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":[0.0001489132,0.0002332486,0.0002524749,0.00006966362,0.0001544624,0.00004546102,0.00006178876,0.0003176949,0.00005245664],"category_scores_gemma":[0.000007412766,0.0002430725,0.0000951047,0.000210034,0.00002197095,0.0002313198,0.00002248386,0.0004227662,0.0001257563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001629289,"about_ca_system_score_gemma":0.00001350747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001127201,"about_ca_topic_score_gemma":0.00003015191,"domain_scores_codex":[0.9988384,0.00006724249,0.0002586761,0.0002776551,0.0001269845,0.0004310974],"domain_scores_gemma":[0.9995251,0.00004849307,0.00006626012,0.000236743,0.00005141227,0.00007196626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001752016,0.000004974278,0.00002049513,0.00001447447,0.0000492462,0.0000153834,0.00008671088,0.7600429,0.03688329,0.000002521275,0.0005163811,0.2023461],"study_design_scores_gemma":[0.0005250278,0.00002319399,0.0005507146,0.000072926,0.00003089893,0.00008857766,0.00005341909,0.9949371,0.001942543,0.00002951798,0.001466752,0.0002793136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2732872,0.0002254317,0.7194077,0.00004270245,0.005187882,0.0002256485,8.546259e-7,0.0008416615,0.0007809181],"genre_scores_gemma":[0.9656916,0.0000713336,0.03183342,0.00007562857,0.002039594,3.725113e-8,0.00003565203,0.00006463453,0.0001880952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6924044,"threshold_uncertainty_score":0.9912208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01067714942454933,"score_gpt":0.2366706807346833,"score_spread":0.225993531310134,"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."}}