{"id":"W3095304272","doi":"10.1167/jov.20.11.906","title":"Perceptual independence increases with depth in a generative adversarial network","year":2020,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Perception; Coding (social sciences); Neural coding; Image (mathematics); Generative grammar; Artificial neural network; Encoding (memory); Mathematics; Computer vision; Statistics; 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":[0.002459744,0.001069804,0.000685058,0.0004476582,0.0003243802,0.0008056989,0.001021907,0.0008133096,0.001592763],"category_scores_gemma":[0.01148698,0.0008627817,0.0006741905,0.0002582225,0.001324906,0.0018309,0.002146273,0.002742457,0.0002775013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001013521,"about_ca_system_score_gemma":0.0004841775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002014875,"about_ca_topic_score_gemma":0.001724174,"domain_scores_codex":[0.99925,0.0002397441,0.00002845272,0.0001940269,0.0001839048,0.0001037823],"domain_scores_gemma":[0.9936721,0.004314954,0.000734683,0.000648348,0.0003695099,0.0002604137],"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":[0.0004374482,0.0001120169,0.004684133,0.0001063461,0.0001108051,0.0001767875,0.000262726,0.9073172,0.04183854,0.009915292,0.0009277189,0.03411103],"study_design_scores_gemma":[0.00001107775,0.00007040451,0.001819068,0.00000876269,0.00001557599,0.00003934415,0.000009346213,0.9873195,0.003616273,0.006922273,0.0001562366,0.00001219068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5494535,0.000328106,0.4435904,0.0008365362,0.00005538811,0.000101419,0.0001962635,0.0007000729,0.004738306],"genre_scores_gemma":[0.9732075,0.0001067045,0.02495181,0.0001560901,0.00001407096,0.00004164903,0.0001568443,0.00007037829,0.001294961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002459744,"threshold_uncertainty_score":0.01300853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008787562140756208,"score_gpt":0.2715571092828689,"score_spread":0.2627695471421126,"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."}}