{"id":"W4384704143","doi":"10.3138/cjpe.71619","title":"How to Conduct a Metaevaluation?: A Metaevaluation Practice","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Strengths and weaknesses; Computer science; Evaluation methods; Quality (philosophy); Process (computing); Management science; Process management; Psychology; Reliability engineering; Social psychology; Business; Engineering","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","insufficient_payload"],"category_scores_codex":[0.1200444,0.000232178,0.0004551502,0.002832953,0.0004189421,0.001883744,0.000823913,0.000122231,0.002146788],"category_scores_gemma":[0.1274006,0.0001829034,0.0002571116,0.005142368,0.00008354901,0.00289185,0.00003431151,0.0002986996,0.001257917],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001249022,"about_ca_system_score_gemma":0.01415346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003092427,"about_ca_topic_score_gemma":0.008229631,"domain_scores_codex":[0.9826341,0.002760812,0.00147262,0.000462598,0.01211401,0.0005559006],"domain_scores_gemma":[0.9665969,0.001423344,0.001356489,0.0006158876,0.02901885,0.0009884953],"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":[0.00004325135,0.00004935063,0.0007975313,0.000005121112,0.0001305147,0.00001445862,0.003112932,0.01496511,0.0004673669,0.001447683,0.07079294,0.9081737],"study_design_scores_gemma":[0.001572164,0.001066627,0.02240196,0.00004507059,0.0006043797,0.00009929321,0.008631141,0.1383503,0.0003820533,0.01705907,0.8094543,0.0003336845],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5542017,0.001846753,0.02378293,0.372121,0.009968706,0.0135015,0.00006982961,0.0002262509,0.02428138],"genre_scores_gemma":[0.9763773,0.000019533,0.01980483,0.001351782,0.0004887189,0.0004087924,0.00003897043,0.0000291018,0.00148099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9078401,"threshold_uncertainty_score":0.9995197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.718641825237931,"score_gpt":0.625746580813898,"score_spread":0.09289524442403296,"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."}}