{"id":"W2137207467","doi":"10.1080/15305058.2014.977444","title":"Explore the Usefulness of Person-Fit Analysis on Large-Scale Assessment","year":2014,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Mental Health Research Topics","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Health Evaluation and Outcome Sciences; University of Alberta","funders":"","keywords":"Item response theory; Scale (ratio); Psychology; Econometrics; Statistics; Psychometrics; Developmental psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.05024396,0.0005829573,0.0006077781,0.002282026,0.00089678,0.001425701,0.0007361777,0.0005775121,0.002219973],"category_scores_gemma":[0.1836652,0.0002545913,0.001417972,0.001873532,0.001304727,0.002071483,0.001634846,0.001337492,0.0002439903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012277,"about_ca_system_score_gemma":0.001590971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00668305,"about_ca_topic_score_gemma":0.01012355,"domain_scores_codex":[0.9638001,0.02901836,0.001351269,0.001335371,0.004092183,0.0004027237],"domain_scores_gemma":[0.7359005,0.2290809,0.01058292,0.01459672,0.008705566,0.001133321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006930951,0.0003342919,0.8890489,0.0001345959,0.0007396505,0.0001817715,0.007222434,0.006810475,0.002692989,0.003211068,0.0007327056,0.08819823],"study_design_scores_gemma":[0.00004111027,0.001583077,0.9172494,0.00008732593,0.0001427638,0.0003026621,0.005545057,0.06406844,0.004119236,0.004537971,0.002199115,0.0001237906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9370547,0.00009825474,0.05917822,0.0001441951,0.00003086414,0.0001452923,0.0001938186,0.0001928477,0.002961901],"genre_scores_gemma":[0.9889268,0.00001148059,0.01073558,0.00001491577,0.000004681949,0.00006194379,0.0000809593,0.00002542847,0.0001382051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05024396,"threshold_uncertainty_score":0.2657186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2900361297675365,"score_gpt":0.4846693249959824,"score_spread":0.1946331952284459,"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."}}