{"id":"W3165933122","doi":"10.1111/jpr.12361","title":"History of Psychological Testing from the Perspective of Test Developers in Japan<sup>1</sup>","year":2021,"lang":"en","type":"article","venue":"Japanese Psychological Research","topic":"Innovative Education and Learning Practices","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Intertek (Canada)","funders":"Japan Society for the Promotion of Science","keywords":"Test (biology); Perspective (graphical); Psychology; Psychological testing; Scale (ratio); Wechsler Adult Intelligence Scale; Applied psychology; Intelligence quotient; Social psychology; Developmental psychology; Cognition; Computer science; Artificial intelligence","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007271721,0.0001267107,0.000294691,0.0001647016,0.0002669165,0.00004015015,0.0007696117,0.0002534156,0.003026044],"category_scores_gemma":[0.1071164,0.00008748721,0.00007182905,0.002715039,0.00233444,0.0001490327,0.0001304319,0.00147114,0.00009478071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005800326,"about_ca_system_score_gemma":0.0006887181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006080607,"about_ca_topic_score_gemma":0.0003124606,"domain_scores_codex":[0.9937222,0.003589664,0.0004699609,0.0005935155,0.001100733,0.0005239035],"domain_scores_gemma":[0.9796397,0.01723681,0.0001962762,0.000422925,0.002392684,0.0001115967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0003445008,0.004872261,0.4278994,0.00002119549,0.00004992634,0.00006795176,0.4742267,0.00003706775,0.008818633,0.0444858,0.02581307,0.01336349],"study_design_scores_gemma":[0.0003774375,0.0002634846,0.650923,0.00006512002,0.000004100194,0.000003570895,0.3113186,0.00002345974,0.00004242825,0.002887571,0.033958,0.000133257],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7355046,0.0005582486,0.00000168733,0.009133252,0.0001666725,0.0001940638,0.000004347065,0.00001969314,0.2544175],"genre_scores_gemma":[0.9925009,0.0001079579,0.000983499,0.0005301692,0.0002294493,0.0000379661,0.000004505366,0.000009755746,0.005595812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2569963,"threshold_uncertainty_score":0.9978853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4602770606713116,"score_gpt":0.5499697928962498,"score_spread":0.08969273222493823,"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."}}