{"id":"W4238820305","doi":"10.1177/109821400402500311","title":"Commentary: Minimizing Evaluation Misuse as Principled Practice","year":2004,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Management science; Computer science; Sociology; Economics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05146149,0.0001728499,0.0003958164,0.0005592022,0.0002179653,0.0002551442,0.0004548453,0.00003921416,0.001891687],"category_scores_gemma":[0.01885372,0.0001326994,0.0001753346,0.00123552,0.0001532537,0.001982066,0.0000547012,0.0002721194,0.0002943819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009412289,"about_ca_system_score_gemma":0.002242262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062587,"about_ca_topic_score_gemma":0.00004021624,"domain_scores_codex":[0.9862009,0.002469627,0.001613611,0.0003046525,0.009169579,0.0002416108],"domain_scores_gemma":[0.9867216,0.001619279,0.003348606,0.0004720627,0.007644819,0.0001936408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007735094,0.0005899616,0.00337492,0.000003237973,0.0002019044,0.00001263415,0.008346802,0.1044093,0.002159581,0.0009107261,0.005471374,0.873746],"study_design_scores_gemma":[0.04039069,0.01687083,0.1536892,0.0006496352,0.004328044,0.00223607,0.1554815,0.2436929,0.01018826,0.1389873,0.2315634,0.001922228],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9330601,0.0002038145,0.004345444,0.05492942,0.000812595,0.0006016433,0.000001913846,0.00001102522,0.006034017],"genre_scores_gemma":[0.9737535,0.00007298121,0.01839489,0.007387835,0.0003086499,0.00002256019,0.00001118549,0.00001376172,0.0000346817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8718238,"threshold_uncertainty_score":0.9990207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.191202468548675,"score_gpt":0.5583508310794473,"score_spread":0.3671483625307723,"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."}}