{"id":"W4391220683","doi":"10.1037/apl0001174","title":"An updated meta-analysis of the interrater reliability of supervisory performance ratings.","year":2024,"lang":"en","type":"review","venue":"Journal of Applied Psychology","topic":"Accounting and Organizational Management","field":"Business, Management and Accounting","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Inter-rater reliability; Psychology; Reliability (semiconductor); Meta-analysis; Applied psychology; Social psychology; Statistics; Clinical psychology; Rating scale; Developmental psychology; Medicine; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001685412,0.0003424931,0.002729923,0.001050489,0.00005854942,0.00007424452,0.001141822,0.000211005,0.001069208],"category_scores_gemma":[0.00003029548,0.0001810389,0.001714393,0.002526292,0.0001388892,0.0002789283,0.00023778,0.0005484016,0.00004119066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002815013,"about_ca_system_score_gemma":0.00005273395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001028464,"about_ca_topic_score_gemma":0.00000528965,"domain_scores_codex":[0.9971194,0.00005577188,0.001889471,0.0003394549,0.0004197014,0.0001761864],"domain_scores_gemma":[0.9958683,0.00003831116,0.002897562,0.0006921301,0.0004920667,0.00001163934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004797008,0.002683664,0.002207102,0.07008909,0.5566106,0.00002541452,0.0008236498,0.003866178,0.0001073763,0.02512212,0.1415871,0.196398],"study_design_scores_gemma":[0.0001211245,0.00002394246,0.0004822812,0.0001963868,0.3530113,0.000004464428,0.00005184064,0.0001620187,0.00000247446,0.0004667099,0.645279,0.0001984405],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01107623,0.9649815,0.0003736348,0.0008794442,0.002598684,0.001135612,0.00004528648,0.00006064716,0.01884898],"genre_scores_gemma":[0.3289754,0.6627596,0.000871443,0.004283962,0.00201229,0.0000481989,0.0003015839,0.0002382955,0.0005092456],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.503692,"threshold_uncertainty_score":0.999844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08759989125473523,"score_gpt":0.3357700942884895,"score_spread":0.2481702030337543,"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."}}