{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01881071,0.0001447531,0.0001863952,0.0002665419,0.0005804867,0.00014137,0.0001983847,0.0000427903,0.002388567],"category_scores_gemma":[0.0008508524,0.00009832098,0.00003334891,0.0007224936,0.00007100003,0.0005060572,0.00008183911,0.00009939467,0.00002417788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105441,"about_ca_system_score_gemma":0.001057443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002184543,"about_ca_topic_score_gemma":0.00007142494,"domain_scores_codex":[0.9952013,0.0006533752,0.0008209157,0.0003517653,0.0027868,0.0001857706],"domain_scores_gemma":[0.9963752,0.0002275682,0.0003947084,0.000260679,0.002633242,0.000108583],"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":[0.00007015831,0.000166353,0.01011455,0.000009677096,0.00007141515,0.000005276227,0.3669021,0.02788361,0.0002918035,0.001099259,0.0003834312,0.5930024],"study_design_scores_gemma":[0.0006364544,0.0002044773,0.006628038,0.00003822394,0.00008181721,0.0001580963,0.02691053,0.9519537,0.001525133,0.01117237,0.0005079522,0.0001831796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9571189,0.0000526492,0.03640305,0.0001176911,0.0001828547,0.001601058,0.000007241902,0.0000256233,0.004490922],"genre_scores_gemma":[0.9384346,5.944696e-7,0.06112309,0.0001508219,0.00003294305,0.0001748542,0.0000365796,0.000009047701,0.00003749268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9240701,"threshold_uncertainty_score":0.9985234,"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."}}