{"id":"W2971517022","doi":"10.1177/1098214019866260","title":"Evaluations in the English-Speaking Commonwealth Caribbean Region: Lessons From the Field","year":2019,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Commonwealth; Pride; Nexus (standard); Face (sociological concept); Public relations; Political science; Sociology; Psychology; Social psychology; Social science; Law","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":[],"category_scores_codex":[0.02939576,0.0001181352,0.0003020225,0.0002112065,0.0002047771,0.0002603254,0.0009626947,0.00003379702,0.001120021],"category_scores_gemma":[0.007438891,0.00005926482,0.00014723,0.001277025,0.0001005575,0.000573332,0.00004824345,0.0004652278,0.00008212418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541922,"about_ca_system_score_gemma":0.0008171258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003836093,"about_ca_topic_score_gemma":0.0009055299,"domain_scores_codex":[0.9907645,0.003613057,0.001074686,0.0002155834,0.00414227,0.0001899104],"domain_scores_gemma":[0.9852945,0.01037187,0.001550384,0.0007366632,0.001993438,0.0000531269],"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":[0.0001102214,0.0001013154,0.2132199,0.00000107535,0.00004317016,0.00000269485,0.04831369,0.01409465,0.00004423306,0.001799048,0.01459488,0.7076751],"study_design_scores_gemma":[0.001431923,0.0009020899,0.8187229,0.00009469385,0.0001272922,0.00002597402,0.08027123,0.05187843,0.00003738908,0.01155749,0.0347821,0.0001684932],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.912735,0.0002097115,0.002096794,0.07606922,0.0008425427,0.0005031081,0.000003683607,0.000004821316,0.00753509],"genre_scores_gemma":[0.9932316,0.00005019708,0.0003137209,0.005934393,0.0004095969,0.00001465553,0.000006444624,0.000006504833,0.00003286759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7075067,"threshold_uncertainty_score":0.9997931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2049595892506882,"score_gpt":0.5292134531119421,"score_spread":0.3242538638612539,"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."}}