{"id":"W2228177330","doi":"10.3138/cjpe.026.003","title":"Addressing the Challenges Encountered During a Developmental Evaluation: Implications for Evaluation Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Perspective (graphical); Evaluation methods; Program evaluation; Psychology; Government (linguistics); Engineering ethics; Knowledge management; Process management; Medical education; Management science; Political science; Computer science; Business; Medicine; Engineering; Public administration","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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06105339,0.0001934133,0.0002478096,0.0006278952,0.00104611,0.0005016755,0.0007829093,0.0001102865,0.002143599],"category_scores_gemma":[0.01770287,0.0001367549,0.000173379,0.0007156166,0.0001335987,0.001806705,0.00002410161,0.0002284314,0.00004619433],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001535137,"about_ca_system_score_gemma":0.01370103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001932257,"about_ca_topic_score_gemma":0.01139883,"domain_scores_codex":[0.9924338,0.001787579,0.001392782,0.0003701077,0.003624445,0.0003912543],"domain_scores_gemma":[0.9806253,0.0008318463,0.001586492,0.0004561114,0.01616287,0.000337357],"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":[0.00007216813,0.00008925286,0.002636459,0.000008188193,0.00009501636,6.305231e-7,0.01188258,0.0006519701,0.00008240125,0.001246967,0.001025982,0.9822084],"study_design_scores_gemma":[0.006938099,0.0008579902,0.7095754,0.0002314063,0.001611388,0.000524817,0.04764554,0.1163642,0.0005412564,0.07073297,0.04440452,0.0005724671],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8328425,0.01546782,0.005574405,0.046295,0.004659841,0.02348775,0.00006661622,0.00006322526,0.07154284],"genre_scores_gemma":[0.9853213,0.00005337842,0.01237875,0.0002323169,0.0003143947,0.00161963,0.00002353596,0.00001875551,0.00003789574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9816359,"threshold_uncertainty_score":0.9987686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8348360624185777,"score_gpt":0.6002670065070299,"score_spread":0.2345690559115478,"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."}}