{"id":"W2278381810","doi":"10.1002/ev.20158","title":"Assessing the Practice Impact of Research on Evaluation","year":2015,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Evaluation methods; Program evaluation; Psychology; Applied psychology; Computer science; Political science; Public administration; Reliability engineering; 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":[0.1363261,0.0001246237,0.0001843619,0.0007253175,0.0005902221,0.0005644747,0.0004022713,0.00008864773,0.0009687738],"category_scores_gemma":[0.0782761,0.00007504276,0.0001816336,0.002562855,0.00009757536,0.001777695,0.00004383408,0.0002418452,0.0002397557],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147903,"about_ca_system_score_gemma":0.005921238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004554048,"about_ca_topic_score_gemma":0.0001362,"domain_scores_codex":[0.9844223,0.004374872,0.0007865654,0.0004409667,0.009705986,0.0002693584],"domain_scores_gemma":[0.9732386,0.008652723,0.0005587357,0.0008078654,0.0165972,0.000144912],"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":[0.0002084419,0.0002652725,0.002055082,0.000002455305,0.00006822788,5.364864e-8,0.002552198,0.1836199,0.0002455624,0.002425811,0.1086735,0.6998835],"study_design_scores_gemma":[0.002833281,0.001043572,0.06293412,0.00003792742,0.0002043318,0.000006957615,0.01094069,0.8076981,0.0006344976,0.07064318,0.04288464,0.0001387279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7026923,0.0007861179,0.02127291,0.0186942,0.003574813,0.00707513,0.00002096266,0.00009542397,0.2457881],"genre_scores_gemma":[0.9958755,0.00001262826,0.00168673,0.00009992368,0.0004209589,0.0003986408,0.00003755301,0.00001354178,0.001454461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6997447,"threshold_uncertainty_score":0.9999444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8085447410014557,"score_gpt":0.7537715169629834,"score_spread":0.05477322403847229,"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."}}