{"id":"W2942721804","doi":"10.1109/cvprw.2019.00068","title":"Towards Computer Vision Powered Color-Nutrient Assessment of Puréed Food","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Institute for Aging; University of Waterloo","funders":"","keywords":"Autoencoder; Artificial intelligence; Computer science; Computer vision; Nutrient; Deep learning; Agricultural engineering; Engineering; Biology","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":[0.0006736035,0.0007320358,0.0003366908,0.00055666,0.0001623462,0.0008985183,0.0005817218,0.0008127693,0.001110121],"category_scores_gemma":[0.001595688,0.0002843501,0.0002266117,0.0003559527,0.0003953108,0.0009781963,0.0007951364,0.0005172737,0.0005372707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003503885,"about_ca_system_score_gemma":0.0004027069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002599214,"about_ca_topic_score_gemma":0.005880146,"domain_scores_codex":[0.9997271,0.00005469193,0.00001077235,0.0001062549,0.00008124126,0.00001990455],"domain_scores_gemma":[0.9994712,0.0001560194,0.00008156014,0.00006120806,0.0001971089,0.00003283551],"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":[0.0008062231,0.000334984,0.01892514,0.0002214244,0.0001451284,0.0002023929,0.0002460259,0.02461837,0.6912153,0.001369775,0.001295809,0.2606194],"study_design_scores_gemma":[0.00003971437,0.0005569285,0.02793211,0.00003785266,0.0001033826,0.0005423501,0.0001630272,0.6587548,0.3032143,0.004810614,0.003777554,0.0000673514],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4284932,0.0006182357,0.5650893,0.0003507416,0.00005900622,0.0001090997,0.0003539073,0.001866428,0.003060058],"genre_scores_gemma":[0.6557578,0.0003656375,0.3393304,0.0002143538,0.00002673662,0.00006288583,0.0003217122,0.0001175032,0.003803017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002599214,"threshold_uncertainty_score":0.0051682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01186948121559648,"score_gpt":0.2694008346027771,"score_spread":0.2575313533871806,"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."}}