{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006537333,0.002220593,0.001303794,0.003122701,0.0005270173,0.002269987,0.00315542,0.001067674,0.01087105],"category_scores_gemma":[0.01463829,0.001092324,0.001413862,0.001636193,0.0007678183,0.002491195,0.001982624,0.001204623,0.004522168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001312203,"about_ca_system_score_gemma":0.002238619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005957555,"about_ca_topic_score_gemma":0.004162471,"domain_scores_codex":[0.9965535,0.0007433873,0.0004258973,0.0005370665,0.001569598,0.0001705781],"domain_scores_gemma":[0.9943831,0.001936234,0.0004248873,0.001088556,0.002034198,0.0001330972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002422708,0.0005441121,0.007262535,0.001486904,0.0007134441,0.0004065239,0.0005773774,0.1450914,0.0425732,0.01685157,0.1984351,0.5836352],"study_design_scores_gemma":[0.0003227565,0.000494009,0.004741507,0.000142779,0.0001260619,0.0003764469,0.0001389732,0.8377104,0.1004591,0.01015739,0.04514035,0.0001902432],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.02570954,0.0002702152,0.6559259,0.0001948189,0.0001357966,0.0004871664,0.006651191,0.3059021,0.004723301],"genre_scores_gemma":[0.2098259,0.0003427244,0.7116647,0.0003304324,0.00006247449,0.001931899,0.03170212,0.03781029,0.006329362],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01087105,"threshold_uncertainty_score":0.0363673,"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."}}