{"id":"W2188387579","doi":"10.3138/cjpe.019.002","title":"Reporting on Outcomes: Setting Performance Expectations and Telling Performance Stories","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Canada","funders":"","keywords":"Outcome (game theory); Chart; Public relations; Actuarial science; Business; Psychology; Political science; Economics; Microeconomics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0141548,0.0001526749,0.0002869089,0.0006951425,0.0006547028,0.0004552597,0.0002574006,0.00006630614,0.0001733925],"category_scores_gemma":[0.006707187,0.0001153633,0.00008894204,0.0006148996,0.00009660298,0.001083278,0.00001093261,0.000283894,0.0000390632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004796234,"about_ca_system_score_gemma":0.003421588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001209069,"about_ca_topic_score_gemma":0.001979388,"domain_scores_codex":[0.9953899,0.0001596489,0.001926901,0.0002377942,0.001978777,0.0003069764],"domain_scores_gemma":[0.9946496,0.0002519746,0.002481395,0.000257917,0.002009096,0.000349948],"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":[0.00001076868,0.00002609826,0.2800477,0.000009756869,0.00001991084,0.000004961333,0.006424821,0.03151759,0.00001985446,0.000220507,0.00006768226,0.6816303],"study_design_scores_gemma":[0.001840081,0.001491561,0.8909363,0.0003684623,0.0001026799,0.0001795554,0.01601203,0.08072186,0.000848031,0.002707003,0.004422542,0.0003698901],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946532,0.0002018398,0.0005174054,0.001668336,0.0006848122,0.0005423995,0.000001664828,0.00001376931,0.00171654],"genre_scores_gemma":[0.991978,0.00001600867,0.007561838,0.0001535012,0.0001439078,0.00004358854,0.000005142505,0.00001136837,0.00008667346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6812605,"threshold_uncertainty_score":0.8029613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4090562215533984,"score_gpt":0.5347074822731473,"score_spread":0.125651260719749,"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."}}