{"id":"W4413757834","doi":"10.1038/s41598-025-17445-9","title":"Heterogeneous dual-decoder network for road extraction in remote sensing images","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Extraction (chemistry); Dual (grammatical number); Artificial intelligence; Computer vision","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005359897,0.001382429,0.000863846,0.001439839,0.0004565073,0.000857841,0.001929947,0.001203726,0.002685481],"category_scores_gemma":[0.001865614,0.0004458876,0.0007509087,0.00100858,0.000450482,0.001830565,0.001658911,0.001143743,0.001901777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006629596,"about_ca_system_score_gemma":0.0009414635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007095004,"about_ca_topic_score_gemma":0.01439633,"domain_scores_codex":[0.9995776,0.00005846937,0.00001621508,0.000150573,0.0001164655,0.00008071128],"domain_scores_gemma":[0.9996464,0.00009644073,0.00002995126,0.00007959863,0.0001198976,0.00002769798],"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":[0.0004999268,0.0003002725,0.004236813,0.0002545504,0.0001757455,0.0004727817,0.0001554263,0.1902667,0.0378285,0.007564203,0.016088,0.7421572],"study_design_scores_gemma":[0.00002204007,0.00006765404,0.001027522,0.00001645799,0.00004894227,0.0001780625,0.00005655516,0.9700086,0.01923841,0.004710749,0.004604999,0.00002006856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06267138,0.000897044,0.9222026,0.0003127802,0.0001491189,0.0001452825,0.001297138,0.00606762,0.006256974],"genre_scores_gemma":[0.5582291,0.0006612317,0.4151172,0.0005271165,0.000130503,0.0002248351,0.008234605,0.0004958568,0.0163796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007095004,"threshold_uncertainty_score":0.01410741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009271732938693152,"score_gpt":0.2609982375264817,"score_spread":0.2517265045877885,"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."}}