{"id":"W4395002215","doi":"10.1111/ijsa.12474","title":"Rating accuracy, leniency, and rater perceptions when using the RPM and BARS","year":2024,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Perception; Applied psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003064672,0.0000694647,0.0001129629,0.0003713554,0.0001870265,0.001059097,0.0001638225,0.00002650908,0.0001831988],"category_scores_gemma":[0.002389045,0.00003849755,0.00004064174,0.0002586299,0.0000547037,0.0004995468,0.0000842119,0.0002383745,6.439737e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004819787,"about_ca_system_score_gemma":0.0000834512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002486655,"about_ca_topic_score_gemma":0.000005178662,"domain_scores_codex":[0.9985377,0.0001980143,0.0004210681,0.0001561868,0.0006055895,0.00008143021],"domain_scores_gemma":[0.9955142,0.003830637,0.0002096393,0.00004364915,0.0003512767,0.00005058661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000282174,0.00003601949,0.1290242,0.000008077728,0.0001672687,0.00002403456,0.002055254,0.0003894184,0.01946527,0.003186531,0.002311992,0.8433037],"study_design_scores_gemma":[0.0009083175,0.0003873741,0.5775607,0.0003258086,0.00009669545,0.006060435,0.01326477,0.287944,0.0004792413,0.07020796,0.04247066,0.0002940181],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8677335,0.0007912976,0.1253578,0.004388649,0.001146978,0.00004501003,0.000002066281,0.000008501279,0.0005261195],"genre_scores_gemma":[0.9660398,0.0003896553,0.03299219,0.0001621516,0.0002843784,9.023477e-7,2.032528e-7,0.000003720768,0.0001269723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8430097,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.368191937024431,"score_gpt":0.5496742645416532,"score_spread":0.1814823275172223,"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."}}