{"id":"W2345157853","doi":"10.1109/tgrs.2016.2514602","title":"Road Network Extraction via Aperiodic Directional Structure Measurement","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Xiamen University; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Aperiodic graph; Computer science; Metric (unit); Artificial intelligence; Computer vision; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002454268,0.0007032667,0.0004984563,0.002976078,0.0003528224,0.0008917365,0.0007070431,0.0005413123,0.001177614],"category_scores_gemma":[0.001552817,0.0003054607,0.0005525287,0.001946112,0.0003489369,0.001527993,0.0009625449,0.0005214936,0.00100929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002758295,"about_ca_system_score_gemma":0.0005265794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001035127,"about_ca_topic_score_gemma":0.002133472,"domain_scores_codex":[0.9995197,0.0000591665,0.00002962737,0.000170232,0.0001785885,0.00004264222],"domain_scores_gemma":[0.9992852,0.0001292059,0.0001383876,0.000195795,0.0002200654,0.00003141491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002001065,0.00008608032,0.007235554,0.0003342503,0.00008207578,0.0003380385,0.0003439439,0.04419289,0.1397734,0.01329046,0.003978775,0.7901444],"study_design_scores_gemma":[0.00002292618,0.0001293599,0.01023883,0.00003943254,0.000074664,0.001009858,0.0002760536,0.8612614,0.08856664,0.01724257,0.02106122,0.0000770554],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03095447,0.0001539526,0.9651424,0.00005509251,0.00002622932,0.00005957705,0.0004026678,0.00110476,0.002100903],"genre_scores_gemma":[0.3331236,0.0003128152,0.6624804,0.00005472443,0.00005451227,0.000121377,0.001621563,0.0002079316,0.002023055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002976078,"threshold_uncertainty_score":0.003939509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01049985138339105,"score_gpt":0.2110720445132491,"score_spread":0.200572193129858,"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."}}