{"id":"W3215944848","doi":"10.2196/31875","title":"Nutrient and Food Group Prediction as Orchestrated by an Automated Image Recognition System in a Smartphone App (CALO mama): Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Nutrient; Food group; Meal; Portion size; Food energy; Artificial intelligence; Mobile apps; Computer science; Food science; Environmental health; Medicine; Biology; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001175493,0.0008287078,0.0005247724,0.0004975918,0.0001762008,0.0004099204,0.0007763692,0.0006781045,0.001038876],"category_scores_gemma":[0.003534618,0.0002470163,0.000543749,0.00022806,0.0003133842,0.0003591382,0.0005019818,0.0003440342,0.0007383793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003321195,"about_ca_system_score_gemma":0.0003293702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00401673,"about_ca_topic_score_gemma":0.004353852,"domain_scores_codex":[0.999278,0.0002032676,0.00005877668,0.0002103742,0.0001772224,0.0000723774],"domain_scores_gemma":[0.998217,0.0006936572,0.0001901758,0.0001940081,0.0006170371,0.00008810711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01145688,0.01002725,0.4765606,0.002486193,0.001297099,0.001854707,0.002639563,0.01692393,0.1940756,0.0003921106,0.006655447,0.2756306],"study_design_scores_gemma":[0.0005343799,0.01528039,0.6568038,0.000181243,0.0007451563,0.002031455,0.0008073783,0.2306834,0.08738187,0.0002283325,0.005163261,0.0001593734],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947814,0.00009894837,0.003702515,0.00002181001,0.00002371346,0.0002482038,0.0004506106,0.0002471987,0.0004254655],"genre_scores_gemma":[0.9764716,0.0001320656,0.02006573,0.0001129013,0.00002397515,0.0003513142,0.001645554,0.00004489119,0.001151967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00401673,"threshold_uncertainty_score":0.007986665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05641019375852432,"score_gpt":0.3838534461212517,"score_spread":0.3274432523627274,"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."}}