{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003952761,0.0001840513,0.0003244356,0.0001252737,0.001470988,0.00009407773,0.0008203181,0.0001938133,0.004480313],"category_scores_gemma":[0.00006208501,0.0001353801,0.000154496,0.00006387685,0.0003248591,0.0002921268,0.00009245425,0.0006219372,0.0005899273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005507084,"about_ca_system_score_gemma":0.00006395915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001162058,"about_ca_topic_score_gemma":0.000003010745,"domain_scores_codex":[0.997949,0.0003702617,0.0006421168,0.0001738992,0.0004593397,0.0004054024],"domain_scores_gemma":[0.9977181,0.000126243,0.001458225,0.0004251394,0.000214617,0.00005767202],"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":[0.001683084,0.0002390583,0.2838082,0.00004400557,0.0009098654,0.00002724874,0.1035422,0.000008280439,0.02020036,0.0004285687,0.05109663,0.5380125],"study_design_scores_gemma":[0.002029362,0.0003849708,0.9913418,0.00003349804,0.0001528509,0.0001113019,0.0003306569,0.0002273905,0.0001270116,0.0005044618,0.004571846,0.0001848233],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9546148,0.00008251139,0.00003892768,0.003658642,0.001432172,0.0001514754,0.000001980336,0.00001241919,0.04000708],"genre_scores_gemma":[0.9916019,0.00001832338,0.0001812375,0.002515298,0.001575857,0.000004675895,0.000002005921,0.00002786403,0.004072857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7075336,"threshold_uncertainty_score":0.9998289,"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."}}