{"id":"W4416444018","doi":"10.1016/j.softx.2025.102445","title":"SegEv: semantic segmentation performance verification and evaluation software","year":2025,"lang":"en","type":"article","venue":"SoftwareX","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Technology Department of Henan Province; Natural Science Foundation of Chongqing; Chinese Aeronautical Establishment; Zhengzhou University; National Natural Science Foundation of China","keywords":"Segmentation; Visualization; Software deployment; Software; Modular design; Key (lock); Ground truth; Feature (linguistics)","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":[0.0002478509,0.0001084287,0.00008993728,0.0001055523,0.0002549819,0.00007844421,0.000291368,0.00004547824,0.000006770431],"category_scores_gemma":[0.00007813092,0.0001131179,0.0000194998,0.0006013506,0.00004035025,0.0006124243,0.0001166158,0.00008755428,0.00003245516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008643966,"about_ca_system_score_gemma":0.00007331285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003021058,"about_ca_topic_score_gemma":0.000002611449,"domain_scores_codex":[0.9989836,0.00005176759,0.000188679,0.0003826655,0.0002298412,0.0001634741],"domain_scores_gemma":[0.999136,0.0001235871,0.00008465303,0.0004634928,0.0001532932,0.00003895416],"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":[0.000005189194,0.00003081557,0.01283274,0.0000535365,0.00001207018,2.916137e-7,0.0002390398,0.002721154,0.00152943,0.006852629,0.0007978018,0.9749253],"study_design_scores_gemma":[0.001115541,0.00008323482,0.2903797,0.0001349566,0.00007037858,0.00001452941,0.00005097275,0.6466648,0.0156603,0.0414942,0.003852042,0.0004793561],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1439669,0.000339772,0.8539206,0.000628355,0.0001696069,0.0004645224,0.000001196702,0.0003250859,0.0001839762],"genre_scores_gemma":[0.8931147,0.000119997,0.1058873,0.0003726857,0.00002552756,0.0002168693,0.00002554599,0.000006884062,0.0002305282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9744459,"threshold_uncertainty_score":0.4612814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01721387233961834,"score_gpt":0.2895209092282574,"score_spread":0.2723070368886391,"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."}}