{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001924997,0.00007655103,0.0001942117,0.0003006866,0.00007215852,0.00003059482,0.0005971738,0.00003518239,0.0006824856],"category_scores_gemma":[0.000610082,0.00005136509,0.0001456119,0.0002744756,0.00004367925,0.00007429058,0.00005530899,0.0003693189,0.00001693861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001241924,"about_ca_system_score_gemma":0.00005717158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007594217,"about_ca_topic_score_gemma":0.00001998269,"domain_scores_codex":[0.9981012,0.0002750247,0.0004448436,0.0001115006,0.0008809078,0.0001864767],"domain_scores_gemma":[0.9974274,0.00115142,0.0005676359,0.0001753901,0.0005962552,0.00008187839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002953483,0.001140337,0.8452838,0.00004539468,0.002434213,0.0001212331,0.008144482,0.00376857,0.0006342431,0.01166414,0.003279607,0.1231886],"study_design_scores_gemma":[0.001562949,0.0008910276,0.9613442,0.0002407135,0.0001755205,0.0001260045,0.007283838,0.02326134,0.0004489701,0.0007441327,0.003786406,0.0001348319],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9718126,0.00003514564,0.008321088,0.003216991,0.001005391,0.0000713212,0.00001127412,0.000006269771,0.01551989],"genre_scores_gemma":[0.9958754,0.000001970633,0.002902396,0.000348192,0.0005130898,0.000005673132,0.00000231693,0.000008338189,0.0003426828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1230538,"threshold_uncertainty_score":0.7472739,"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."}}