{"id":"W4378223570","doi":"10.1002/ev.20540","title":"What we can learn from the international program for development evaluation training (IPDET)","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Program evaluation; Training (meteorology); Monitoring and evaluation; Diversity (politics); Medical education; Corporate governance; Political science; Psychology; Business; Medicine; Geography; Public administration; Finance","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02027583,0.000180733,0.0001945055,0.0003814693,0.0009562689,0.001183605,0.0005673315,0.00009727187,0.001742619],"category_scores_gemma":[0.006198145,0.0001325587,0.0001773384,0.00117908,0.00003853541,0.000978679,0.00006170417,0.0001149685,0.0002619385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005514317,"about_ca_system_score_gemma":0.002484871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006608532,"about_ca_topic_score_gemma":0.003626251,"domain_scores_codex":[0.9940389,0.0003564642,0.0008220404,0.0006102448,0.003863023,0.0003093217],"domain_scores_gemma":[0.9939265,0.002695922,0.0003912886,0.0004291877,0.002459302,0.00009782404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000037923,0.00003987788,0.0003375596,0.000001554949,0.00006255478,2.013879e-8,0.008020009,0.007267925,0.0001297757,0.000216869,0.05327784,0.9306081],"study_design_scores_gemma":[0.001480625,0.00006568262,0.01336402,0.00003419938,0.0000887798,5.442189e-7,0.007277131,0.4473603,0.0003893526,0.02246811,0.5073485,0.0001228005],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6015567,0.001505582,0.05158221,0.262092,0.04319316,0.02989428,0.0002483742,0.001384491,0.008543247],"genre_scores_gemma":[0.8953398,0.0006019179,0.03261326,0.001715562,0.003905639,0.02677898,0.005914544,0.0001050608,0.03302525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9304853,"threshold_uncertainty_score":0.9998533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5304740430548962,"score_gpt":0.569693978952799,"score_spread":0.03921993589790285,"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."}}