{"id":"W2687461486","doi":"10.1080/00224545.2017.1341373","title":"Evaluating performance over time: Is improving better than being consistently good?","year":2017,"lang":"en","type":"article","venue":"The Journal of Social Psychology","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008737455,0.0003870667,0.0006142298,0.001376381,0.001083571,0.003591855,0.0005040658,0.001549398,0.001793283],"category_scores_gemma":[0.02940364,0.000203187,0.0004786612,0.00159991,0.003711195,0.003632545,0.001200249,0.001139628,0.0002047494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378924,"about_ca_system_score_gemma":0.0008900215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00347139,"about_ca_topic_score_gemma":0.005501546,"domain_scores_codex":[0.9949499,0.002651602,0.0003185956,0.0005300064,0.001099258,0.000450606],"domain_scores_gemma":[0.977009,0.00932733,0.007440865,0.001601727,0.002251742,0.002369447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001605956,0.0007836919,0.7486365,0.0005196586,0.0004506183,0.0002830213,0.02037977,0.001035904,0.002954194,0.01313614,0.002723935,0.2074906],"study_design_scores_gemma":[0.00006117276,0.000990986,0.9638248,0.0003056212,0.0002128735,0.0002921299,0.01253733,0.001450165,0.001119336,0.01556723,0.003533818,0.00010458],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9766459,0.001961975,0.001304364,0.003805669,0.0000792864,0.00002082208,0.00004286012,0.00001803286,0.01612107],"genre_scores_gemma":[0.9985934,0.0003647877,0.000495122,0.0002629573,0.00003421683,0.000009602777,0.00001841302,0.000004250584,0.0002173006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008737455,"threshold_uncertainty_score":0.04620868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0837879619350121,"score_gpt":0.4285248106338994,"score_spread":0.3447368486988873,"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."}}