{"id":"W3094954661","doi":"10.1167/jov.20.11.920","title":"A response reclassification procedure to reduce noise caused by guesses","year":2020,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Material Properties and Processing","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Task (project management); Noise (video); Computation; Computer science; Process (computing); Cutoff; Simple (philosophy); Pattern recognition (psychology); Artificial intelligence; Statistics; Speech recognition; Algorithm; Mathematics","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":[0.0002353107,0.00007301029,0.0001232693,0.00004109988,0.00003714277,0.00007532841,0.000107271,0.00004272547,0.00004277044],"category_scores_gemma":[0.0002372263,0.00005592937,0.00002620189,0.0001412961,0.00000549589,0.0002006252,0.00001308435,0.0001012046,0.00001996839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003504018,"about_ca_system_score_gemma":0.00003146416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.679969e-7,"about_ca_topic_score_gemma":9.342121e-8,"domain_scores_codex":[0.9993907,0.00003403956,0.0002679302,0.0000672789,0.0001516605,0.00008842115],"domain_scores_gemma":[0.999628,0.0000198681,0.00007543884,0.0000565741,0.00009124598,0.0001288413],"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":[0.0007477847,0.000008117049,0.000004789072,0.00009070755,0.000005467887,0.000003797836,0.0006865007,0.001153399,0.9357969,6.8823e-7,0.05533195,0.006169889],"study_design_scores_gemma":[0.0006759363,0.0009550059,0.003709999,0.00063335,0.00002476114,0.00003123117,0.0003072436,0.0107387,0.6836569,0.00002954446,0.2989733,0.0002641007],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873356,0.0006662757,0.001820543,0.009658078,0.0002457907,0.00007123538,0.00000326341,0.00004467013,0.0001546087],"genre_scores_gemma":[0.9986155,0.00007514252,0.0007115643,0.0003386395,0.0001868107,0.000001135236,8.578829e-7,0.00001859561,0.00005177017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2521401,"threshold_uncertainty_score":0.2280733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0246919575352346,"score_gpt":0.2680317271759389,"score_spread":0.2433397696407043,"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."}}