{"id":"W4319662944","doi":"10.1016/j.evalprogplan.2023.102257","title":"Learning from experiences of evaluators implementing theory-driven evaluations in diverse settings: Building on the contributions of John Mayne","year":2023,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Honor; Theory of change; Set (abstract data type); Sociology; Engineering ethics; Work (physics); Epistemology; Management science; Psychology; Computer science; Engineering; Philosophy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1342227,0.000864373,0.001895237,0.004419971,0.002479209,0.01027971,0.002379175,0.003525435,0.002599443],"category_scores_gemma":[0.232626,0.0008236035,0.001082129,0.004500172,0.004878542,0.01293799,0.008448322,0.01056909,0.0007731237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005326409,"about_ca_system_score_gemma":0.01995979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00586642,"about_ca_topic_score_gemma":0.03115597,"domain_scores_codex":[0.9133157,0.07024828,0.003443506,0.001659991,0.01044954,0.0008829705],"domain_scores_gemma":[0.5471089,0.399979,0.005898728,0.005355562,0.03752609,0.004131827],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00013013,0.0003349627,0.001600878,0.01498753,0.0003975427,0.0001930397,0.0198425,0.0006757933,0.0003459436,0.04016295,0.07595436,0.8453744],"study_design_scores_gemma":[0.0001469136,0.0004935483,0.003466646,0.08974469,0.0006503331,0.0006676023,0.01791818,0.0006645152,0.001287396,0.06733125,0.8173823,0.0002467553],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004590031,0.7424858,0.02533726,0.2072214,0.003400599,0.0005779366,0.00007550877,0.00006395177,0.01624745],"genre_scores_gemma":[0.05386661,0.8338661,0.05614673,0.04629944,0.001853229,0.00124339,0.00007884944,0.0001308325,0.006514824],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8657773,"threshold_uncertainty_score":0.7098459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3687882346319569,"score_gpt":0.6091828399366908,"score_spread":0.2403946053047338,"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."}}