{"id":"W18830643","doi":"10.3138/cjpe.026.001","title":"Advancing Empirical Scholarship to Further Develop Evaluation Theory and Practice","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Grounded theory; Context (archaeology); Development theory; Field (mathematics); Empirical research; Contingency; Epistemology; Sociology; Intersection (aeronautics); Contingency theory; Management science; Engineering ethics; Qualitative research; Knowledge management; Computer science; Social science; Political science; Economics","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":[0.123081,0.00013875,0.0002115006,0.0008215165,0.0002405246,0.000378912,0.0003749638,0.00009107417,0.003545433],"category_scores_gemma":[0.07867451,0.000108101,0.00005783772,0.001140743,0.00007516366,0.001823277,0.00002333024,0.000260603,0.0001565621],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005323553,"about_ca_system_score_gemma":0.007967063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001158139,"about_ca_topic_score_gemma":0.007066055,"domain_scores_codex":[0.9910715,0.004155572,0.0009729883,0.0002907674,0.003171006,0.0003382128],"domain_scores_gemma":[0.987357,0.001231334,0.0006682547,0.0002901028,0.009655432,0.0007979153],"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":[0.0001218474,0.0000388359,0.02729316,0.000001902025,0.00002783669,0.000004534122,0.01140147,0.0002413089,0.00004289647,0.0006582591,0.0008976988,0.9592702],"study_design_scores_gemma":[0.001834932,0.001408475,0.7638695,0.0001189442,0.0003783461,0.0003487947,0.01839562,0.01073665,0.0002738029,0.1019099,0.100315,0.0004101049],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9583588,0.001152224,0.01218419,0.009083507,0.001217044,0.002492861,0.00000358477,0.00001649766,0.01549134],"genre_scores_gemma":[0.9545121,0.000008134364,0.04362605,0.00155642,0.0001305912,0.00008400523,0.000003412745,0.00001293575,0.00006631498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9588602,"threshold_uncertainty_score":0.9976568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.580695406400756,"score_gpt":0.5966934622915074,"score_spread":0.01599805589075143,"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."}}