{"id":"W2032247159","doi":"10.1332/174426411x603470","title":"The challenges of evaluating large-scale, multi-partner programmes: the case of NIHR CLAHRCs","year":2011,"lang":"en","type":"article","venue":"Evidence & Policy","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; National Institutes of Health; National Institute for Health and Care Research","keywords":"Health care; Psychological intervention; Government (linguistics); Scale (ratio); Public relations; Business; Knowledge management; Political science; Nursing; Medicine; Computer science; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004725046,0.0001880982,0.0003914256,0.00009278974,0.001154571,0.000005976067,0.0005892115,0.0001781778,0.0001178986],"category_scores_gemma":[0.003067719,0.00009917384,0.0001527042,0.0003325877,0.0002952825,0.0002039465,0.0003318012,0.0006118799,0.00007551257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001632423,"about_ca_system_score_gemma":0.002119465,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00787091,"about_ca_topic_score_gemma":0.01123794,"domain_scores_codex":[0.9961739,0.001422279,0.0009873358,0.0002585622,0.0003101508,0.0008477946],"domain_scores_gemma":[0.9946253,0.003061008,0.0007118655,0.000974961,0.0004797102,0.0001471062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0005026042,0.0005605682,0.1020141,0.004233629,0.0001959373,0.00009327426,0.3623075,0.000002550978,0.0002689108,0.1690192,0.01829721,0.3425045],"study_design_scores_gemma":[0.005273365,0.002715233,0.5720908,0.00519406,0.0005700351,0.0002698841,0.2893623,0.00149188,0.0009757098,0.01959756,0.1011737,0.001285522],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7554543,0.08605801,0.0002409544,0.1163519,0.001561137,0.006908149,0.00007949121,0.000266826,0.03307925],"genre_scores_gemma":[0.9869809,0.005201245,0.0014793,0.004285364,0.0004687773,0.0004020086,9.919137e-7,0.00003241007,0.001149015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4700767,"threshold_uncertainty_score":0.9987358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3752349630186249,"score_gpt":0.5553957392407609,"score_spread":0.180160776222136,"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."}}