{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7301786,0.001874394,0.006284974,0.01587693,0.01548614,0.04943062,0.007474562,0.01323625,0.003959014],"category_scores_gemma":[0.6980662,0.003130226,0.001673081,0.009548042,0.1006884,0.05113991,0.04177064,0.02155967,0.00113256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03255483,"about_ca_system_score_gemma":0.05285377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003163849,"about_ca_topic_score_gemma":0.003088337,"domain_scores_codex":[0.1488277,0.7442114,0.02984769,0.01487995,0.05616722,0.006065983],"domain_scores_gemma":[0.1042697,0.791567,0.01907684,0.03203415,0.04314361,0.009908788],"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":[0.0005061971,0.0003378964,0.006145997,0.004396831,0.0003454243,0.0009904495,0.1585471,0.001214275,0.0008063689,0.5191184,0.01231226,0.2952788],"study_design_scores_gemma":[0.0004672955,0.0008581026,0.003915611,0.01289076,0.0001843925,0.001429369,0.1032585,0.004412172,0.001216245,0.7627423,0.1082053,0.000420031],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.04276428,0.04784472,0.275167,0.554916,0.005339212,0.002194999,0.00006547049,0.0005686366,0.07113967],"genre_scores_gemma":[0.7766484,0.01271348,0.1421269,0.05121756,0.004600528,0.006546795,0.00005497956,0.0004960606,0.005595319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2698214,"threshold_uncertainty_score":0.3327379,"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."}}