{"id":"W1494699756","doi":"","title":"ARTICLE 6: METAEVALUATION: EVALUATING THE EVALUATION OF THE PARIS DECLARATION","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Declaration; Strengths and weaknesses; Evaluation methods; Quality (philosophy); Commission; Political science; Psychology; Computer science; Engineering; Law; Social psychology; Reliability 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5713279,0.004928045,0.01048472,0.01747126,0.003605386,0.01565423,0.005437723,0.009600978,0.008759044],"category_scores_gemma":[0.7756259,0.003254164,0.02009687,0.01620328,0.008753151,0.00957015,0.008727165,0.007231039,0.0008327099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02151966,"about_ca_system_score_gemma":0.03110668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005048352,"about_ca_topic_score_gemma":0.008902544,"domain_scores_codex":[0.1704238,0.7364601,0.04595796,0.005926942,0.04020789,0.001023412],"domain_scores_gemma":[0.1590537,0.7364784,0.04135232,0.02918942,0.03179759,0.002128644],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01210614,0.0005478312,0.009364876,0.2743321,0.2140404,0.0005805967,0.007033931,0.0105093,0.001580021,0.06513683,0.04688622,0.3578818],"study_design_scores_gemma":[0.01375717,0.006010898,0.01510983,0.3438233,0.2537829,0.0007425805,0.002712699,0.01596102,0.009964218,0.1388866,0.1977423,0.001506558],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.03144242,0.462569,0.2784951,0.08942761,0.02174931,0.06797106,0.00760045,0.003139909,0.03760501],"genre_scores_gemma":[0.2419786,0.06645507,0.5822576,0.01424167,0.003432978,0.08569507,0.001604863,0.000855185,0.003479035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4286721,"threshold_uncertainty_score":0.5286291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7038098888130093,"score_gpt":0.5979079630601261,"score_spread":0.1059019257528833,"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."}}