{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005416428,0.0001475357,0.000456216,0.0001835693,0.00007749239,0.00006849169,0.0001862416,0.00007688133,0.0001077885],"category_scores_gemma":[0.000899873,0.0001438822,0.0004724688,0.0003939665,0.0001103138,0.0004995735,0.00005396989,0.0003767888,0.00001513301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006940688,"about_ca_system_score_gemma":0.0001032924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008311707,"about_ca_topic_score_gemma":0.000004183731,"domain_scores_codex":[0.9983352,0.0002784547,0.0005997795,0.0001433634,0.0004332135,0.0002099312],"domain_scores_gemma":[0.998106,0.0003251387,0.0005639341,0.000225928,0.0006807626,0.00009824369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007402806,0.0007123514,0.06211374,0.0006778049,0.0005248351,0.001109802,0.0002915312,0.0001318758,0.9017196,0.0001114449,0.001897247,0.02996946],"study_design_scores_gemma":[0.001490319,0.000134367,0.2233221,0.0005004091,0.000199482,0.002048948,0.0002284285,0.000006543621,0.7707529,0.0008647037,0.000296215,0.0001555277],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.886651,0.0006092926,0.1095816,0.00002185281,0.00278503,0.00006699889,0.00001892793,0.00002041257,0.0002449531],"genre_scores_gemma":[0.9799011,0.0000893601,0.01961164,0.00001473485,0.0002634423,0.000001054182,0.000008254146,0.00002449244,0.00008588989],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1612084,"threshold_uncertainty_score":0.5867347,"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."}}