{"id":"W3036485806","doi":"10.1037/xhp0000856","title":"Is zjudge a better prime for JUDGE than zudge is?: A new evaluation of current orthographic coding models.","year":2020,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Human Perception & Performance","topic":"Reading and Literacy Development","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Economic and Social Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Orthographic projection; Coding (social sciences); Prime (order theory); Current (fluid); Computer science; Natural language processing; Artificial intelligence; Mathematics; Engineering; Statistics; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01982632,0.001046177,0.001292646,0.002062346,0.001110684,0.00480034,0.003044643,0.001787658,0.008801645],"category_scores_gemma":[0.04964413,0.000640846,0.0007432186,0.001570189,0.003598658,0.007492348,0.001872564,0.001857425,0.002035649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001809829,"about_ca_system_score_gemma":0.001590787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002533624,"about_ca_topic_score_gemma":0.001883375,"domain_scores_codex":[0.9959493,0.001174019,0.0002769223,0.001270198,0.001208339,0.0001212711],"domain_scores_gemma":[0.9539218,0.03114193,0.00588587,0.005039582,0.003192557,0.000818276],"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":[0.01701383,0.00100521,0.05706728,0.003786741,0.001142682,0.0008627036,0.006207445,0.003298903,0.04799179,0.2150882,0.01131004,0.6352252],"study_design_scores_gemma":[0.001744068,0.004824541,0.1281799,0.001491031,0.002387977,0.005105206,0.005100782,0.1417993,0.03738062,0.6323025,0.0389237,0.0007605019],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6654911,0.04097147,0.1675773,0.02854728,0.003646028,0.0006718539,0.001590496,0.001329996,0.09017451],"genre_scores_gemma":[0.9586455,0.006355416,0.02776419,0.003268813,0.0005877693,0.0001547494,0.0005276483,0.0002215468,0.002474464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01982632,"threshold_uncertainty_score":0.1048528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2192166758702141,"score_gpt":0.4501757246706802,"score_spread":0.2309590488004661,"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."}}