{"id":"W2116343005","doi":"10.1177/1356389012453289","title":"Towards an evidence base of theory-driven evaluations: Some questions for proponents of theory-driven evaluation","year":2012,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Management science; Causality (physics); Psychological intervention; Promotion (chess); Development theory; Theory of change; Computer science; Psychology; Engineering ethics; Sociology; Political science; Economics; Economic growth; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7093204,0.003338019,0.01104978,0.01812806,0.006242353,0.03477867,0.01479882,0.0208576,0.005633152],"category_scores_gemma":[0.755809,0.003597219,0.005564645,0.010141,0.05336834,0.05038716,0.01930399,0.04186271,0.001681712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02995321,"about_ca_system_score_gemma":0.04820923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005641839,"about_ca_topic_score_gemma":0.003887157,"domain_scores_codex":[0.3859683,0.4765062,0.0368845,0.01207714,0.08469865,0.003865279],"domain_scores_gemma":[0.09353103,0.8119583,0.01256628,0.02626317,0.05276982,0.002911423],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002916491,0.0003736715,0.001469461,0.0118393,0.0008075616,0.000141197,0.008957516,0.003707259,0.0002147868,0.8249243,0.008801457,0.1384717],"study_design_scores_gemma":[0.0004843321,0.0003081688,0.0004870823,0.02402098,0.0002978761,0.00007275811,0.003408711,0.008307198,0.0008118667,0.9302331,0.03142024,0.0001478334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.005944031,0.04586648,0.4266109,0.4900143,0.00454776,0.003031636,0.0002383735,0.000400048,0.02334655],"genre_scores_gemma":[0.2208776,0.01946955,0.688532,0.05678952,0.002238032,0.009718457,0.0002855858,0.0003572194,0.00173209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2906796,"threshold_uncertainty_score":0.3584597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3773650039081808,"score_gpt":0.5722308654359345,"score_spread":0.1948658615277536,"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."}}