{"id":"W2126226185","doi":"10.1167/8.12.8","title":"Maximum differentiation (MAD) competition: A methodology for comparing computational models of perceptual quantities","year":2008,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Howard Hughes Medical Institute","keywords":"Stimulus (psychology); Perception; Computational model; Computer science; Strengths and weaknesses; Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Machine learning; Cognitive psychology; Psychology; Neuroscience; Social psychology","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":[0.01070829,0.001659062,0.001422558,0.002355644,0.0007063205,0.001662086,0.003280522,0.001320475,0.003382671],"category_scores_gemma":[0.02878749,0.0006438341,0.001527531,0.001279604,0.001775372,0.002234705,0.00349647,0.001854055,0.0003696841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002084397,"about_ca_system_score_gemma":0.001630528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001542593,"about_ca_topic_score_gemma":0.001871264,"domain_scores_codex":[0.9964911,0.001931471,0.0001971094,0.0003661663,0.0008428956,0.0001712182],"domain_scores_gemma":[0.9883146,0.008372284,0.0008078374,0.001662894,0.0005197133,0.0003226459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009319936,0.0003135909,0.00606496,0.000789117,0.0006178508,0.000178099,0.0003328616,0.5024281,0.04376701,0.339566,0.002249768,0.1027607],"study_design_scores_gemma":[0.00009358471,0.0004531609,0.001342963,0.00002464964,0.00003385017,0.0000979037,0.00003343147,0.8703744,0.006474994,0.1192542,0.001762111,0.00005481889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0346218,0.0001623369,0.9614587,0.0001588421,0.00003496034,0.0001875642,0.0002444302,0.0004262345,0.00270508],"genre_scores_gemma":[0.4728544,0.0001457813,0.5238848,0.0001992122,0.00003755271,0.001298348,0.0004764194,0.0002600709,0.0008433352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01070829,"threshold_uncertainty_score":0.05663151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3043467223196251,"score_gpt":0.4031572376372731,"score_spread":0.098810515317648,"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."}}