{"id":"W3102015017","doi":"10.3138/cjpe.61723","title":"Anticipating and Addressing Stakeholders’ Stereotypes of Evaluation","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perception; Process (computing); Psychology; Focus (optics); Applied psychology; Knowledge management; Social psychology; Public relations; Computer science; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01576436,0.0000977372,0.0002550548,0.0003722111,0.0001437949,0.0002791646,0.0001999865,0.00005577373,0.001506144],"category_scores_gemma":[0.00555069,0.00007835988,0.0000702759,0.0006264579,0.0000986505,0.0006800175,0.00001350248,0.0001495552,0.000009215393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001154148,"about_ca_system_score_gemma":0.003477943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001763856,"about_ca_topic_score_gemma":0.00209044,"domain_scores_codex":[0.9952951,0.0007306159,0.001012802,0.0001809001,0.00259888,0.0001817008],"domain_scores_gemma":[0.9942778,0.0002402332,0.001076169,0.0001459437,0.00384747,0.0004123325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001661555,0.00001382675,0.03704786,0.00001368182,0.0000228245,0.000001744885,0.004993834,0.003140699,0.0002853249,0.00007782943,0.0005219223,0.9538639],"study_design_scores_gemma":[0.00177489,0.0009174995,0.1614045,0.000158527,0.0002596739,0.00002154718,0.00713078,0.820401,0.0006078466,0.003136179,0.004022873,0.0001647458],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912761,0.0009585619,0.001663316,0.003482596,0.0002880712,0.0008615734,0.000006190024,0.00000492417,0.001458669],"genre_scores_gemma":[0.9958214,0.000006945552,0.003799068,0.0002138475,0.0001218409,0.00001558634,0.000006443446,0.000007318699,0.000007581717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9536991,"threshold_uncertainty_score":0.9994066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8194598612454987,"score_gpt":0.5817553033009218,"score_spread":0.2377045579445769,"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."}}