{"id":"W3127972227","doi":"10.1016/j.joen.2020.11.028","title":"Effectiveness of Commercial Software–Enhanced Image Artifact Reduction Software","year":2021,"lang":"en","type":"article","venue":"Journal of Endodontics","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artifact (error); Software; Cone beam computed tomography; Computer science; Materials science; Artificial intelligence; Medicine; Computed tomography; Radiology","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":[0.001408449,0.0006388205,0.0003895411,0.001273745,0.0002136285,0.001142352,0.0005763969,0.000952774,0.004778636],"category_scores_gemma":[0.009832994,0.0002919237,0.0005735568,0.0006189272,0.0002714917,0.0008937619,0.0005768481,0.0003063964,0.0007976058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002354324,"about_ca_system_score_gemma":0.0004355384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187131,"about_ca_topic_score_gemma":0.0009608745,"domain_scores_codex":[0.9985141,0.0003923503,0.0001620965,0.0002095097,0.0006410275,0.00008094931],"domain_scores_gemma":[0.9925631,0.004051039,0.0004075772,0.0006408037,0.002214002,0.0001233926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00785892,0.000706023,0.007011734,0.0007532382,0.0002310994,0.0004144728,0.0002285163,0.005726166,0.3201086,0.0007771195,0.002333633,0.6538505],"study_design_scores_gemma":[0.0007636499,0.007328771,0.0744822,0.0001662853,0.001174445,0.006218466,0.0003550818,0.2141866,0.6774297,0.0009844395,0.01665441,0.0002561073],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8835132,0.003336448,0.09889882,0.0003518812,0.0003159522,0.0001635246,0.0003562748,0.00479982,0.00826403],"genre_scores_gemma":[0.9116184,0.0008276535,0.08088636,0.0002391199,0.00009003156,0.00004850256,0.000762123,0.0009466041,0.004581224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004778636,"threshold_uncertainty_score":0.01598608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01249591901354404,"score_gpt":0.2822784949191886,"score_spread":0.2697825759056446,"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."}}