{"id":"W4413360974","doi":"10.1177/10982140251355140","title":"Theory-Practice Connections in Collaborative Approaches to Evaluation: A Systematic Review of Practice","year":2025,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Systematic review; Management science; Psychology; Evaluation methods; Program evaluation; Peer evaluation; Computer science; Engineering ethics; MEDLINE; Political science; Higher education; Engineering","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1373821,0.0001447037,0.0008875931,0.001011449,0.00009388689,0.0001016009,0.0004188419,0.00003244486,0.0005245454],"category_scores_gemma":[0.2178106,0.0001044448,0.0001321293,0.006078054,0.0001141301,0.00135452,0.00004877531,0.0002184459,0.00004280578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005038938,"about_ca_system_score_gemma":0.003473639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001559548,"about_ca_topic_score_gemma":0.00002699936,"domain_scores_codex":[0.976343,0.01484664,0.002871713,0.0002913763,0.005487799,0.000159457],"domain_scores_gemma":[0.965926,0.01338631,0.004552295,0.0005673129,0.01547985,0.00008822717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0039893,0.003856218,0.001801657,0.02836148,0.002784575,0.00001696668,0.05819022,0.1189707,0.0004553052,0.2068201,0.0194007,0.5553527],"study_design_scores_gemma":[0.007531355,0.006215972,0.01133263,0.1929282,0.01436432,0.0003957196,0.5635684,0.1207961,0.0007035065,0.06838824,0.01276924,0.0010064],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.0806444,0.1044661,0.1492071,0.3967833,0.003897605,0.02502102,0.00004401034,0.00003942833,0.239897],"genre_scores_gemma":[0.9785444,0.001535738,0.01271032,0.006671746,0.00005379899,0.0003140249,0.00000451559,0.000008658731,0.0001568574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8978999,"threshold_uncertainty_score":0.8882467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3195343202464981,"score_gpt":0.545800497569362,"score_spread":0.2262661773228639,"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."}}