{"id":"W2781180907","doi":"10.15353/vsnl.v3i1.183","title":"Goldilocks and the Three Parameters:Empirically Finding the \"Just Right\" for Segmenting Food Images for the AFINI-T System","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Weighting; Segmentation; Artificial intelligence; Market segmentation; Computer science; Regularization (linguistics); Goldilocks principle; Computer vision; Pattern recognition (psychology); Statistics; Business; Mathematics; Marketing; Medicine","routes":{"ca_aff":false,"ca_fund":true,"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":[0.00395742,0.001112602,0.001246003,0.001319119,0.001063409,0.002447379,0.001639695,0.00284176,0.001838795],"category_scores_gemma":[0.01772579,0.0006765627,0.0005964246,0.0006951374,0.001267205,0.002879744,0.001506894,0.001487357,0.0004856692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001438695,"about_ca_system_score_gemma":0.001581481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01262849,"about_ca_topic_score_gemma":0.01422027,"domain_scores_codex":[0.9984842,0.0004297005,0.0001106265,0.0004922295,0.0002745123,0.0002088774],"domain_scores_gemma":[0.9967424,0.001794546,0.0003452933,0.0004799073,0.0004996198,0.0001381827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002200297,0.0005512295,0.02912085,0.0006401876,0.000329825,0.0003933217,0.0004985517,0.3052069,0.0629084,0.01277212,0.005791238,0.5795872],"study_design_scores_gemma":[0.0000675641,0.0001781609,0.005028437,0.00004983765,0.0000518633,0.0002310418,0.00008964833,0.9705434,0.01899049,0.003658416,0.001070589,0.00004053148],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3693995,0.002409412,0.6182436,0.00132788,0.0001700654,0.0004111595,0.0002935682,0.002767717,0.004977047],"genre_scores_gemma":[0.6637874,0.0003616102,0.3327928,0.00041928,0.00004356388,0.0001297189,0.0003838759,0.0002564162,0.001825457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01262849,"threshold_uncertainty_score":0.02511001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0402296305299808,"score_gpt":0.333227829162056,"score_spread":0.2929981986320752,"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."}}