{"id":"W2913663231","doi":"10.1177/1356389019827035","title":"Combining internal and external evaluations within a multilevel evaluation framework: Computational text analysis of lessons from the Asian Development Bank","year":2019,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Lee Kuan Yew School of Public Policy, National University of Singapore; Whitney and Betty MacMillan Center for International and Area Studies; Yale University","keywords":"Macro; Psychological intervention; Micro level; Scenario analysis; Political science; Computer science; Process management; Psychology; Business; Economics; Finance; Microeconomics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02834314,0.0002242461,0.0004417207,0.000650504,0.0003550012,0.0003328435,0.0005607258,0.0001231204,0.009750921],"category_scores_gemma":[0.004233858,0.0001598184,0.0001540067,0.001407794,0.0001108253,0.0005883819,0.0001599292,0.0002821353,0.0002558053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000283426,"about_ca_system_score_gemma":0.00134975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066851,"about_ca_topic_score_gemma":0.000424523,"domain_scores_codex":[0.9881575,0.001862814,0.00152885,0.0006789352,0.007554268,0.0002176348],"domain_scores_gemma":[0.9914562,0.003700934,0.001190047,0.0006476837,0.002910672,0.00009443977],"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":[0.00005770374,0.0001077981,0.1784794,0.000002543168,0.0005105262,1.027697e-7,0.01957304,0.3695074,0.0003901339,0.003953611,0.0001510129,0.4272667],"study_design_scores_gemma":[0.0006807516,0.00003299894,0.4732638,0.00005620252,0.000472909,5.568133e-7,0.001541178,0.5043526,0.00009519552,0.01933669,0.00006954982,0.00009759523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8683612,0.0001872273,0.1259358,0.002374948,0.0005571313,0.001076096,0.00004142172,0.00001681593,0.001449303],"genre_scores_gemma":[0.9784667,0.000004444834,0.02046063,0.0004065557,0.00006133234,0.0001380267,0.0002860427,0.00001248249,0.0001637499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4271691,"threshold_uncertainty_score":0.9911543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2313179511134962,"score_gpt":0.5268569038509368,"score_spread":0.2955389527374405,"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."}}