{"id":"W2083111387","doi":"10.1016/j.evalprogplan.2011.03.003","title":"Using hybrid models to support the development of organizational evaluation capacity: A case narrative","year":2011,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Work (physics); Narrative; Process management; Program evaluation; Public sector; Internal validity; Knowledge management; Management science; Computer science; Business; Engineering; Political science; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01871469,0.0007198474,0.00048127,0.001811452,0.001720492,0.006506319,0.002844573,0.001610906,0.003788383],"category_scores_gemma":[0.04357271,0.0005500317,0.0007576264,0.001976795,0.002066392,0.00598645,0.0045802,0.002610876,0.0003889179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005181927,"about_ca_system_score_gemma":0.004421104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006912949,"about_ca_topic_score_gemma":0.01368323,"domain_scores_codex":[0.985715,0.01170659,0.00040891,0.0003971184,0.001210975,0.0005613363],"domain_scores_gemma":[0.9390249,0.05080999,0.001528176,0.004004634,0.003684765,0.0009474972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0008597332,0.001004821,0.02558038,0.0005582261,0.0002405918,0.001755835,0.01137405,0.3565975,0.001734847,0.4426678,0.004568864,0.1530573],"study_design_scores_gemma":[0.0001568583,0.0005407039,0.003042617,0.0004113089,0.0001172421,0.0005027313,0.007222646,0.8161168,0.003929307,0.1448129,0.02302411,0.000122923],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4439176,0.000814906,0.4618955,0.006309414,0.0001256367,0.001143265,0.0004291416,0.0003801596,0.08498434],"genre_scores_gemma":[0.8442671,0.0001647722,0.1528562,0.0001179361,0.00000982949,0.0003846862,0.00009524322,0.00004596315,0.002058131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01871469,"threshold_uncertainty_score":0.09897387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7330308143647964,"score_gpt":0.5574659762554713,"score_spread":0.1755648381093251,"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."}}