{"id":"W4400223184","doi":"10.1167/jov.24.7.2","title":"TORONTO: A trial-oriented multidimensional psychometric testing algorithm","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; King's College London","keywords":"Computer science; Algorithm; Psychometric testing; Psychology; Clinical psychology; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007659969,0.0001425644,0.0003399699,0.0001598808,0.00006458316,0.0000515484,0.0001071013,0.00007245238,0.000385644],"category_scores_gemma":[0.00237671,0.0000907662,0.0001798722,0.0007008246,0.0000316105,0.0002486077,0.00004260741,0.0002868078,0.00003781947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001289975,"about_ca_system_score_gemma":0.00006322554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001860046,"about_ca_topic_score_gemma":7.161779e-7,"domain_scores_codex":[0.9981142,0.00007824624,0.000730072,0.0001657612,0.0007079463,0.0002037675],"domain_scores_gemma":[0.9964484,0.002747857,0.000206068,0.0001095591,0.0002991328,0.0001890007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001004362,0.0006195469,0.00001096568,0.00006194269,0.00008388544,0.0002058783,0.00009016762,0.000001472376,0.001084524,0.004263561,0.01175318,0.9808205],"study_design_scores_gemma":[0.05957739,0.02344231,0.006216449,0.004282862,0.0008157062,0.002460589,0.0004586739,0.4716122,0.0008736191,0.2964912,0.1323583,0.001410689],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06784721,0.005005053,0.9186134,0.0004343938,0.00600663,0.0003677576,0.00003294517,0.0001399626,0.00155269],"genre_scores_gemma":[0.01918821,0.00008360736,0.9789229,0.00005682995,0.001179315,0.000003000242,0.000001494343,0.00003322485,0.0005314391],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9794098,"threshold_uncertainty_score":0.4222531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05223546547664389,"score_gpt":0.383665724284288,"score_spread":0.3314302588076441,"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."}}