{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07391463,0.0010956,0.001392357,0.002376089,0.000999385,0.00192565,0.001385652,0.0007236894,0.001046613],"category_scores_gemma":[0.07571443,0.0003677369,0.001773051,0.00217452,0.0008635716,0.001296556,0.001670906,0.001125485,0.0004097524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002672621,"about_ca_system_score_gemma":0.007105644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00583303,"about_ca_topic_score_gemma":0.01565642,"domain_scores_codex":[0.941552,0.03922247,0.005467454,0.001476041,0.01094405,0.001338037],"domain_scores_gemma":[0.9291062,0.03009646,0.009581631,0.003385164,0.02611321,0.001717316],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004503138,0.01394472,0.4739698,0.002553158,0.0008271309,0.00007752485,0.003481614,0.002233689,0.006811981,0.0009739587,0.002464105,0.4881591],"study_design_scores_gemma":[0.0008067132,0.02987164,0.9253783,0.001024808,0.000920872,0.0001321418,0.003943947,0.007465696,0.02316529,0.001177573,0.005940187,0.0001728685],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9203777,0.00361615,0.04942853,0.001231394,0.0002704493,0.0142375,0.001618663,0.0002858595,0.008933725],"genre_scores_gemma":[0.9147949,0.001378636,0.07373325,0.0003182945,0.00009638203,0.007138889,0.001142296,0.00008476152,0.001312568],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9260854,"threshold_uncertainty_score":0.3909026,"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."}}