{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.172752,0.0001765508,0.0002940622,0.0003908202,0.0006715104,0.0003435683,0.0008653156,0.0001120078,0.003856596],"category_scores_gemma":[0.02330954,0.00009501661,0.0002960271,0.001812749,0.0002240274,0.001470737,0.00003676559,0.0003320452,0.000079874],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008936226,"about_ca_system_score_gemma":0.009686183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003129401,"about_ca_topic_score_gemma":0.004348504,"domain_scores_codex":[0.9785022,0.006217617,0.001930879,0.0002203951,0.01267289,0.0004560923],"domain_scores_gemma":[0.9798374,0.0008476868,0.002233223,0.0007934531,0.01595152,0.0003367521],"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":[0.00002155724,0.00008615927,0.08393175,0.000003832372,0.00007338699,6.993813e-8,0.00421017,0.03074289,0.0006221831,0.001130213,0.002777255,0.8764005],"study_design_scores_gemma":[0.001281096,0.0003334343,0.5114548,0.00004366725,0.001016052,0.00003047176,0.002593945,0.4612365,0.001821183,0.01312138,0.00692505,0.0001423481],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825568,0.002636092,0.000995877,0.005009449,0.002339849,0.002812149,0.000005006285,0.000006866466,0.003637875],"genre_scores_gemma":[0.9973382,0.000007731987,0.001636329,0.0002399304,0.0004610987,0.0002093993,0.000005783524,0.00001315698,0.0000883145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8762582,"threshold_uncertainty_score":0.997054,"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."}}