{"id":"W4316813279","doi":"10.3390/jimaging9020020","title":"Verification, Evaluation, and Validation: Which, How & Why, in Medical Augmented Reality System Design","year":2023,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Augmented reality; Virtual reality; Human–computer interaction; Key (lock); Observer (physics); Software engineering; Computer security","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005973398,0.00008399543,0.000176769,0.0003902935,0.00009033522,0.00008608605,0.0001280951,0.00005402794,0.001232432],"category_scores_gemma":[0.0009745022,0.00007702049,0.00003726014,0.000481772,0.00003158769,0.0003264983,0.00001698973,0.0002398439,0.00009978368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001820095,"about_ca_system_score_gemma":0.000143541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002525903,"about_ca_topic_score_gemma":0.00001928537,"domain_scores_codex":[0.9975065,0.0009364263,0.0006167381,0.0001473522,0.0006538607,0.0001391468],"domain_scores_gemma":[0.9982423,0.0002690375,0.0004422598,0.0001720169,0.0007673745,0.0001069955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0004988092,0.0003589603,0.06171307,0.0002101193,0.0003737095,0.0002088416,0.02224276,0.002061856,0.001888871,0.008931635,0.807478,0.09403342],"study_design_scores_gemma":[0.007110227,0.00007814613,0.7441372,0.000989122,0.000154896,0.002362218,0.01711134,0.1401442,0.0003178784,0.001129556,0.08602238,0.0004428276],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3468899,0.0006882267,0.4416912,0.1841292,0.00782056,0.001107545,0.00001300543,0.0003988313,0.01726151],"genre_scores_gemma":[0.9988451,0.00002486582,0.0003624668,0.0002484817,0.0002057857,0.00001650897,0.00001586762,0.00001074693,0.0002701541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7214556,"threshold_uncertainty_score":0.9996806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1014873274066052,"score_gpt":0.4263075144564643,"score_spread":0.324820187049859,"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."}}