{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000406293,0.00009167167,0.000306087,0.0002027127,0.0002004237,0.00002167128,0.0001424016,0.00006024108,0.000104154],"category_scores_gemma":[0.0001718705,0.00007782094,0.0001374897,0.0001061672,0.0001130237,0.0003690847,0.00002725037,0.0001282422,0.000003939713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002804142,"about_ca_system_score_gemma":0.00005839707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001805425,"about_ca_topic_score_gemma":8.635453e-7,"domain_scores_codex":[0.9986448,0.0002276861,0.0005126157,0.0001249655,0.0003764053,0.000113471],"domain_scores_gemma":[0.99871,0.0004221702,0.0004805799,0.00005779615,0.0002757182,0.0000536957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007537927,0.0004352086,0.0002132772,0.0001314957,0.00001418148,0.000007460045,0.004609356,0.04971834,0.8939427,0.0469559,0.0005115298,0.002706732],"study_design_scores_gemma":[0.00390665,0.002887583,0.01716269,0.0003512395,0.00006030943,0.001045431,0.001396026,0.6974193,0.06088175,0.2143363,0.0002294903,0.0003232888],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5350815,0.00001871661,0.4643945,0.0001153357,0.0002355733,0.00004966106,0.000004116171,0.000008160681,0.0000924532],"genre_scores_gemma":[0.9617785,0.00005329811,0.03782967,0.0001737807,0.00009375559,0.000001245617,0.00000500073,0.000009751942,0.00005497714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.833061,"threshold_uncertainty_score":0.3173446,"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."}}