{"id":"W2920077988","doi":"10.3138/cjpe.53070","title":"How We Model Matters: A Manifesto for the Next Generation of Program Theorizing","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Manifesto; Sociology; Epistemology; Scale (ratio); Engineering ethics; Computer science; Political science; Law; Philosophy; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.01190438,0.0001245368,0.0002312102,0.0003900656,0.000199703,0.0008930155,0.0005328915,0.0000733669,0.0003466246],"category_scores_gemma":[0.00091945,0.00007754261,0.0001922986,0.0004432249,0.00007338283,0.001049777,0.00001160315,0.0001441828,0.00001875217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002133502,"about_ca_system_score_gemma":0.002761089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007823927,"about_ca_topic_score_gemma":0.00331831,"domain_scores_codex":[0.9967915,0.0002812779,0.0007467429,0.0001936624,0.001729505,0.0002573522],"domain_scores_gemma":[0.9952627,0.0003681952,0.0009480029,0.0003641715,0.002863353,0.0001935912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002237348,0.0000403628,0.001231302,0.00001492643,0.00003986383,3.602474e-7,0.001374237,0.02975335,0.0009324981,0.002489317,0.005059359,0.9590421],"study_design_scores_gemma":[0.0007511756,0.0006346413,0.001083187,0.00004762301,0.00009995811,0.00001399245,0.002360075,0.9467334,0.0002726646,0.008275365,0.03962965,0.00009833817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7653458,0.002939935,0.09150346,0.1204037,0.003802947,0.01475952,0.00003842808,0.00003263684,0.001173518],"genre_scores_gemma":[0.9799933,0.00002482475,0.01857193,0.0003458799,0.0002812015,0.000273791,0.0000123696,0.00001335998,0.0004833028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9589437,"threshold_uncertainty_score":0.8611369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.63617589694431,"score_gpt":0.5222816882781216,"score_spread":0.1138942086661884,"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."}}