{"id":"W7161179859","doi":"10.1109/asim67379.2025.11512828","title":"Intelligent Feature Segmentation Technology for Hilly and Mountainous Areas Based on Deep Learning","year":2025,"lang":"","type":"article","venue":"","topic":"AI and Multimedia in Education","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Department of Environment and Conservation","funders":"","keywords":"Deep learning; Feature (linguistics); Segmentation; Pattern recognition (psychology); Field (mathematics); Image segmentation","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":[0.0002841274,0.0002405005,0.0002065261,0.0005957635,0.0004155409,0.0001986467,0.0003518811,0.0002997322,0.00003134643],"category_scores_gemma":[0.0004243068,0.0002296758,0.00005908899,0.0007032091,0.0001110083,0.0001753158,0.0001155287,0.0003326827,0.00001326361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002516993,"about_ca_system_score_gemma":0.0002528648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002227466,"about_ca_topic_score_gemma":0.00002607724,"domain_scores_codex":[0.9984856,0.00006321274,0.0002609477,0.00066055,0.0001731364,0.0003565878],"domain_scores_gemma":[0.9986737,0.0005038397,0.0001362413,0.0003481664,0.0002575063,0.00008055152],"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":[0.00005454869,0.0002137666,0.004229253,0.00009723045,0.00003031886,0.000001118655,0.00130929,0.003947055,0.0003801649,0.01723614,0.0006195584,0.9718816],"study_design_scores_gemma":[0.0006972945,0.0006445104,0.001832492,0.0001369316,0.00004760114,0.000003362122,0.001932273,0.9678917,0.01437855,0.003337535,0.008851167,0.0002465646],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00860897,0.0006600434,0.9658854,0.02047358,0.00171825,0.001096977,0.000001700621,0.0001539947,0.001401091],"genre_scores_gemma":[0.8553842,0.000191819,0.1380675,0.001917616,0.00009765894,0.0002438426,0.0000265337,0.00001375876,0.004057093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.971635,"threshold_uncertainty_score":0.9365909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009167360315565434,"score_gpt":0.2820525721167865,"score_spread":0.2728852118012211,"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."}}