{"id":"W4386092750","doi":"10.1038/s41598-023-40839-6","title":"A deep learning framework to scale linear facial measurements to actual size using horizontal visible iris diameter: a study on an Iranian population","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Face recognition and analysis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Concordia University","funders":"","keywords":"Magnification; IRIS (biosensor); Pixel; Artificial intelligence; Range (aeronautics); Digital photography; Computer science; Mathematics; Computer vision; Photography; Materials science; Biometrics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00230291,0.0002032222,0.0002733627,0.0007164716,0.0008523783,0.001081443,0.000363533,0.00007343035,0.00004964535],"category_scores_gemma":[0.0008621595,0.0001991364,0.0001308537,0.0037546,0.00002371084,0.0005267377,0.0002431658,0.0001919304,0.0003166489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388577,"about_ca_system_score_gemma":0.00005598594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002090498,"about_ca_topic_score_gemma":0.0002598978,"domain_scores_codex":[0.9960742,0.0002138032,0.0005124188,0.001293525,0.001424974,0.0004811084],"domain_scores_gemma":[0.9982973,0.00005661028,0.0001839551,0.0008487944,0.0002104139,0.0004028741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000083372,0.001867906,0.39178,0.00003101986,0.000203164,0.001149162,0.05939278,0.1454554,0.1147789,0.00001275379,0.0005892359,0.2846563],"study_design_scores_gemma":[0.001304626,0.004168088,0.3421283,0.0006200944,0.000268716,0.0001579542,0.01446361,0.6086808,0.01783112,0.003319406,0.003854066,0.003203195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8950611,0.000001666373,0.1014431,0.0001039374,0.002539438,0.0004907555,0.000001107874,0.0003112246,0.00004772863],"genre_scores_gemma":[0.9698662,1.297682e-7,0.02960497,0.00007644076,0.0001109257,0.00002400527,0.00001486675,0.00001894735,0.0002835024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4632254,"threshold_uncertainty_score":0.9999555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05801119425753908,"score_gpt":0.3275380107208403,"score_spread":0.2695268164633012,"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."}}