{"id":"W2132391446","doi":"10.1037/0021-9010.93.3.711","title":"Using frame-of-reference training to understand the implications of rater idiosyncrasy for rating accuracy.","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Psychology","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Idiosyncrasy; Normative; Psychology; Frame of reference; Frame (networking); Relational frame theory; Applied psychology; Cognitive psychology; Computer science; Epistemology","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":[],"consensus_categories":[],"category_scores_codex":[0.003267059,0.000080563,0.0003141213,0.0002223932,0.0001746251,0.00002109937,0.0005378918,0.00006396533,0.0002213668],"category_scores_gemma":[0.0004248831,0.00004804912,0.00009015504,0.0004231438,0.0001241223,0.0001171412,0.00002700195,0.000165949,0.000005733384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000232569,"about_ca_system_score_gemma":0.0002667198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001047951,"about_ca_topic_score_gemma":0.000003893851,"domain_scores_codex":[0.9980298,0.00007959108,0.001091031,0.0001475451,0.0005016199,0.0001504321],"domain_scores_gemma":[0.996293,0.001544249,0.001195397,0.0003111523,0.0005956167,0.0000605957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002007914,0.000419172,0.0155588,0.00002640334,0.0003039408,0.000002860917,0.07400417,0.03482718,0.5812995,0.09328,0.02113676,0.1771332],"study_design_scores_gemma":[0.0100497,0.002920232,0.4217845,0.0001965045,0.0002715114,0.001008974,0.08529468,0.008042775,0.03504163,0.3680468,0.06643952,0.0009031296],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7688605,0.00003059834,0.222356,0.002398283,0.0002017861,0.0002251215,0.000006258543,0.000001927888,0.005919595],"genre_scores_gemma":[0.9718624,0.00001870816,0.02700809,0.0009986575,0.00008187234,0.000005056045,4.26131e-7,0.000005752613,0.00001903632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5462579,"threshold_uncertainty_score":0.2423811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7397751505922106,"score_gpt":0.6055301082324799,"score_spread":0.1342450423597307,"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."}}