{"id":"W2332681108","doi":"10.3138/cjpe.30.2.228","title":"Trevisan, M. S., &amp; Walser, T. M. (2015) <i>Evaluability assessment: Improving evaluation quality and use.</i>","year":2015,"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":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Philosophy; Epistemology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1315307,0.0002711448,0.0005567903,0.0007850798,0.0003508092,0.001499679,0.0005510934,0.0001725865,0.002003888],"category_scores_gemma":[0.02885576,0.0002161927,0.0001863378,0.001024414,0.0002304225,0.002728225,0.0000464808,0.0004238061,0.00006949462],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001667895,"about_ca_system_score_gemma":0.01765365,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002535575,"about_ca_topic_score_gemma":0.03634752,"domain_scores_codex":[0.984957,0.004638206,0.002296644,0.0005485074,0.007064892,0.0004947225],"domain_scores_gemma":[0.9807506,0.000852989,0.001878694,0.0007734802,0.0143401,0.001404121],"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":[0.00003409127,0.00007699148,0.1584422,0.00001146918,0.00003341709,0.000001166529,0.000994954,0.001670126,0.00007902474,0.0003451781,0.005508496,0.832803],"study_design_scores_gemma":[0.004146789,0.0007345823,0.7006008,0.00006562821,0.0004392274,0.00006924092,0.001810032,0.1545275,0.00004128695,0.0318545,0.105256,0.0004543817],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811114,0.001815964,0.003738194,0.005587001,0.001787317,0.003032283,0.00002661629,0.00002575417,0.002875451],"genre_scores_gemma":[0.9850796,0.00001810249,0.01382082,0.0003948555,0.0002762434,0.0001415247,0.0000587167,0.00001947285,0.0001906748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8323485,"threshold_uncertainty_score":0.9995369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6893862509287247,"score_gpt":0.6140360373202267,"score_spread":0.07535021360849803,"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."}}