{"id":"W2902911821","doi":"10.3138/cjpe.42238","title":"Readiness in Evaluation: Three Prompts for Evaluators","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Agency (philosophy); Process (computing); Tacit knowledge; Psychology; Knowledge management; Power (physics); Public relations; Process management; Computer science; Business; Sociology; 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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0634971,0.0001839266,0.0003625362,0.001427281,0.0002920798,0.0004368742,0.0007109609,0.0001351671,0.004513991],"category_scores_gemma":[0.01149536,0.0001455891,0.0001638622,0.001624234,0.0002010507,0.0009628531,0.00001489015,0.0001889806,0.0001271397],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009836396,"about_ca_system_score_gemma":0.01336575,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003880509,"about_ca_topic_score_gemma":0.1245348,"domain_scores_codex":[0.9925593,0.0008169703,0.001573049,0.0003704815,0.004219698,0.0004604635],"domain_scores_gemma":[0.9834032,0.0004213898,0.000971183,0.0004668885,0.01428263,0.00045469],"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":[0.00005849727,0.00005550038,0.05328471,0.000005511319,0.00002349021,0.000001441512,0.001112785,0.001220029,0.00003359584,0.0005938663,0.004704949,0.9389056],"study_design_scores_gemma":[0.003993281,0.001714853,0.2812471,0.0001229824,0.0001966492,0.00003758544,0.0009069071,0.563053,0.0002200274,0.09448003,0.05374289,0.0002847502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.974455,0.0006214544,0.004366106,0.004274212,0.003394602,0.006868071,0.00001466527,0.00001409073,0.005991822],"genre_scores_gemma":[0.9922478,0.000002455108,0.006028073,0.0001818686,0.0007800759,0.000612942,0.00002182996,0.00001760577,0.0001073254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9386209,"threshold_uncertainty_score":0.9968312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5904033203647878,"score_gpt":0.6029827397166689,"score_spread":0.01257941935188112,"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."}}