{"id":"W4411918728","doi":"10.1016/j.evalprogplan.2025.102647","title":"Evaluating sport-for-development outcome measures used in a living lab setting: Process, improvements, and insights","year":2025,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Physical Activity and Health","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Maple Leaf Medical Clinic; St. Joseph’s Healthcare Hamilton","funders":"Mitacs; Canada Research Chairs","keywords":"Outcome (game theory); Process (computing); Psychology; Process management; Engineering; Management science; Applied psychology; Engineering ethics; Risk analysis (engineering); Computer science; Business; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.002328746,0.0001271119,0.0002876032,0.0001562229,0.0001997157,0.00005280895,0.00002983896,0.00006782674,0.000004462789],"category_scores_gemma":[0.0005676482,0.0001110037,0.00001973417,0.0002082333,0.0000257491,0.0001296588,0.0000307532,0.0001846269,4.85102e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008874316,"about_ca_system_score_gemma":0.0004020233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001395138,"about_ca_topic_score_gemma":0.00002245876,"domain_scores_codex":[0.9986733,0.00006334187,0.0003607543,0.0002951273,0.0003891741,0.0002183048],"domain_scores_gemma":[0.9994032,0.0001691717,0.0001147023,0.00007667789,0.0001593378,0.00007692882],"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":[0.0001427841,0.0003625059,0.4273425,0.0009831298,0.00004698641,0.000001428536,0.01143984,0.00004971717,0.0008144241,0.0002026475,0.00001509664,0.558599],"study_design_scores_gemma":[0.004480974,0.0007958403,0.8899145,0.002908884,0.0001776803,0.000003220519,0.002330753,0.09321526,0.0008760305,0.001937787,0.00308473,0.000274376],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959882,0.0007673847,0.0001488375,0.000501297,0.00004547389,0.002035384,6.361482e-7,0.00006453378,0.0004482368],"genre_scores_gemma":[0.9951315,0.000007941066,0.003890718,0.0003179881,0.00003214974,0.0004926335,0.00003245717,0.000008467466,0.00008617291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5583246,"threshold_uncertainty_score":0.4526601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2079077422699825,"score_gpt":0.5085714861958927,"score_spread":0.3006637439259101,"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."}}