{"id":"W2148996827","doi":"10.1111/j.1468-2389.2012.00604.x","title":"<scp>A</scp>ssessing the <scp>R</scp>eliability of <scp>S</scp>ituational <scp>J</scp>udgment <scp>T</scp>ests <scp>U</scp>sed in <scp>H</scp>igh‐<scp>S</scp>takes <scp>S</scp>ituations","year":2012,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Medical Education and Admissions","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Golder Associates (Canada); Saint Mary's University","funders":"","keywords":"Psychology; Reliability (semiconductor)","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","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.01019225,0.003861826,0.004721224,0.00492567,0.002814061,0.002190059,0.00385547,0.002534777,0.0004057958],"category_scores_gemma":[0.1068847,0.003412529,0.002630299,0.005195329,0.001883861,0.004526126,0.001174264,0.008217096,0.0005036897],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.00427229,"about_ca_system_score_gemma":0.009793469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004952263,"about_ca_topic_score_gemma":0.0003921624,"domain_scores_codex":[0.9679423,0.003042859,0.008941508,0.00376752,0.01107571,0.005230103],"domain_scores_gemma":[0.9241039,0.04971629,0.0086348,0.00258896,0.007869945,0.007086118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004920677,0.02140291,0.1430175,0.001707269,0.006718458,0.0005012992,0.03896197,0.004541697,0.03866244,0.01068451,0.7265943,0.007158362],"study_design_scores_gemma":[0.01278789,0.001941098,0.1884015,0.003435254,0.002273755,0.002694031,0.09896459,0.0101437,0.02060693,0.003916373,0.6545317,0.0003032074],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.912662,0.007723317,0.01409626,0.004302952,0.01191074,0.004575859,0.0008088487,0.0007378294,0.04318218],"genre_scores_gemma":[0.9159082,0.0061469,0.009414665,0.006946258,0.009098465,0.001098526,0.002026052,0.0007908439,0.04857007],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09669247,"threshold_uncertainty_score":0.9995501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607348700990223,"score_gpt":0.3616105198973577,"score_spread":0.3255370328874554,"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."}}