{"id":"W2318178033","doi":"10.1177/1098214013503698","title":"Managing Tensions Between Evaluation and Research","year":2013,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Temporality; Psychological intervention; Software deployment; Process (computing); Management science; Psychology; Sociology; Engineering ethics; Computer science; Epistemology","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":[],"category_scores_codex":[0.0714384,0.00009767957,0.0002996108,0.001007779,0.0002824999,0.000345456,0.0002885809,0.00003088338,0.002648975],"category_scores_gemma":[0.007943246,0.00006804329,0.0000693434,0.001450344,0.0002749547,0.001163496,0.00007774925,0.0003136753,0.0002954354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002051427,"about_ca_system_score_gemma":0.0006851025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008395674,"about_ca_topic_score_gemma":0.00001099213,"domain_scores_codex":[0.9870958,0.003116668,0.001003921,0.0002454733,0.008301758,0.0002364139],"domain_scores_gemma":[0.9841439,0.002339619,0.0009366369,0.0003390058,0.0120529,0.0001879187],"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":[0.000009274296,0.00001772143,0.03604556,8.460693e-7,0.00002069804,2.988441e-7,0.0008528112,0.0009483931,0.0004935671,0.00010987,0.00267784,0.9588231],"study_design_scores_gemma":[0.0007420568,0.0007018202,0.7268568,0.00004206871,0.0001018288,0.00002521892,0.009414387,0.1674901,0.0001289241,0.09252984,0.001857337,0.0001096267],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802135,0.0001993876,0.002174156,0.01175668,0.0002013404,0.0005508481,8.954883e-7,0.000004927162,0.004898242],"genre_scores_gemma":[0.9969881,0.00006887534,0.002331134,0.0001933768,0.0002484659,0.00002850989,0.000003385901,0.00000810423,0.0001300541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9587135,"threshold_uncertainty_score":0.9982628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4777265607402056,"score_gpt":0.6157514516411698,"score_spread":0.1380248909009642,"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."}}