{"id":"W2945590379","doi":"10.3138/cjpe.53169","title":"Anne Markiewicz and Ian Patrick. (2016). <i>Developing Monitoring and Evaluation Frameworks</i> .","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sociology; Psychology; Environmental ethics; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.02341288,0.0001583682,0.0002834142,0.0007127736,0.0002404665,0.0007321034,0.0002586086,0.0001831643,0.0009362936],"category_scores_gemma":[0.002396365,0.0001285897,0.00006141421,0.0007192661,0.00006983977,0.00108672,0.00002380424,0.0003812455,0.00005198913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000416905,"about_ca_system_score_gemma":0.004007644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001672665,"about_ca_topic_score_gemma":0.0007948722,"domain_scores_codex":[0.9952849,0.0006487225,0.0008971205,0.0003091275,0.002547225,0.0003128797],"domain_scores_gemma":[0.9948875,0.0003241504,0.0007072281,0.0002702476,0.003356574,0.0004543059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001028538,0.000008045622,0.1666404,0.000008388583,0.00001887262,0.000001333264,0.00092661,0.0005010816,0.00004600624,0.0001240561,0.0005813634,0.8311335],"study_design_scores_gemma":[0.002341093,0.0006366154,0.8108869,0.0003854809,0.0002209268,0.0001048432,0.004346906,0.1153264,0.0001448025,0.01936464,0.04584135,0.0004001174],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865752,0.005018654,0.0006664264,0.003196156,0.001669073,0.001495318,0.000003321999,0.000008852363,0.001367041],"genre_scores_gemma":[0.9917065,0.0001338471,0.007566867,0.000140698,0.0002675623,0.00004560436,0.000006529002,0.00001243421,0.0001199735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8307334,"threshold_uncertainty_score":0.999977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2223609311383748,"score_gpt":0.4917329420662098,"score_spread":0.269372010927835,"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."}}