{"id":"W4403250772","doi":"10.1002/ev.20615","title":"Using contribution analysis to assess evaluation capacity outcomes in community organizations","year":2024,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"","keywords":"Evaluation methods; Capacity building; Program evaluation; Process management; Business; Political science; Public administration; Economic growth; Economics; Engineering","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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03135104,0.0002006722,0.0004017927,0.002616893,0.0007694029,0.0007013812,0.0003223823,0.000133221,0.002142202],"category_scores_gemma":[0.01838579,0.0001777741,0.0002203951,0.01170647,0.00003059056,0.001116545,0.00005686581,0.0002654117,0.0001573973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001742847,"about_ca_system_score_gemma":0.00158961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001332677,"about_ca_topic_score_gemma":0.01498995,"domain_scores_codex":[0.9929721,0.002189526,0.001041582,0.0005216671,0.002995895,0.000279171],"domain_scores_gemma":[0.9918265,0.002260649,0.0002093682,0.0006749226,0.004878069,0.0001504596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003914364,0.0004004596,0.1195667,0.00001375354,0.0006275058,1.648663e-7,0.005168595,0.735638,0.003727194,0.005949491,0.002740212,0.1261288],"study_design_scores_gemma":[0.0006976324,0.0000531409,0.2391568,0.00001952055,0.001082934,0.000001079018,0.0006029268,0.7393069,0.0005010961,0.01564433,0.00277178,0.0001619168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6357742,0.00007385741,0.3583024,0.001597394,0.001198804,0.00195158,0.00007559378,0.0001011463,0.0009250299],"genre_scores_gemma":[0.9932098,0.000006105072,0.005123807,0.0001587548,0.0001183004,0.0004079335,0.0003806132,0.00001832878,0.0005763966],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3574356,"threshold_uncertainty_score":0.99877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.538010031454944,"score_gpt":0.5850516251312451,"score_spread":0.04704159367630112,"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."}}