{"id":"W2919316438","doi":"10.3138/cjpe.52946","title":"Using Actor-Based Theories of Change to Conduct Robust Evaluation in Complex Settings","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Theory of change; Democracy; Management science; Computer science; Psychological intervention; Process management; Sociology; Operations research; Business; Risk analysis (engineering); Political science; Economics; Psychology; Management; Mathematics; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02935395,0.0001365608,0.0003542662,0.001370027,0.00008731398,0.0001956837,0.0004205964,0.00008156753,0.00516839],"category_scores_gemma":[0.003054036,0.0001117952,0.0001050651,0.001384441,0.00007024145,0.0007741345,0.00001349553,0.0001642238,0.00004565926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007504324,"about_ca_system_score_gemma":0.005517053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001092077,"about_ca_topic_score_gemma":0.01382545,"domain_scores_codex":[0.9941851,0.001073314,0.00113593,0.0002334254,0.003087193,0.0002850565],"domain_scores_gemma":[0.9933407,0.0003024253,0.0009710562,0.0003228837,0.004764558,0.0002983191],"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":[0.00008632374,0.00009187051,0.2329136,0.00002940337,0.00002811089,0.000002101505,0.005677781,0.1646518,0.003230715,0.0007943336,0.0006542801,0.5918397],"study_design_scores_gemma":[0.001971305,0.0006721533,0.2688283,0.0001897558,0.00008196938,0.00001016714,0.003402985,0.7147289,0.0005200219,0.004031066,0.005370786,0.0001926291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924901,0.0001423871,0.0009085916,0.002223197,0.0006352767,0.002691471,0.00001326365,0.000004061136,0.0008917177],"genre_scores_gemma":[0.9892964,9.105789e-7,0.0100545,0.000432919,0.0001041399,0.00006089969,0.00002460729,0.00001076939,0.00001487729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.591647,"threshold_uncertainty_score":0.9994844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8242816801062659,"score_gpt":0.5913763997790368,"score_spread":0.2329052803272291,"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."}}