{"id":"W4353055504","doi":"10.3138/cjpe.75430","title":"Causality and Complexity in Evaluating Equity Interventions: Conceptual Issues That Need to Be Addressed in Theory-Driven Evaluation Approaches","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Causality (physics); Variety (cybernetics); Psychological intervention; Equity (law); Management science; Causal model; Conceptual framework; Risk analysis (engineering); Positive economics; Psychology; Computer science; Sociology; Economics; Political science; Business; Medicine; Social science","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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09844063,0.0001998431,0.0004680933,0.00197355,0.0002195252,0.000526997,0.0005483606,0.0001233358,0.001781604],"category_scores_gemma":[0.01422471,0.0001747459,0.0001403404,0.002326746,0.000277806,0.0009436707,0.0001006982,0.0003474602,0.00004060772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009573661,"about_ca_system_score_gemma":0.003084084,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00168248,"about_ca_topic_score_gemma":0.1661876,"domain_scores_codex":[0.9885309,0.004868226,0.001682547,0.0004614891,0.003954289,0.00050249],"domain_scores_gemma":[0.9956864,0.0008232879,0.0007720643,0.0003592086,0.001911556,0.0004475013],"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":[0.0000947511,0.000114589,0.1411962,0.00003008858,0.00003664455,0.000006787333,0.01916421,0.03206704,0.00007355578,0.004319743,0.001314621,0.8015818],"study_design_scores_gemma":[0.001892026,0.0004918664,0.5385117,0.0002405413,0.00007140198,0.000006819384,0.02555742,0.3828309,0.00004334376,0.04963478,0.0005388537,0.00018035],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866945,0.0006195554,0.0004411816,0.007808607,0.0004597086,0.003093811,0.00002538566,0.00001799248,0.0008392673],"genre_scores_gemma":[0.996694,0.00001390453,0.002481309,0.0001932157,0.00008304773,0.0003709172,0.00007556356,0.000013162,0.00007493045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8014014,"threshold_uncertainty_score":0.9991309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.921309918994153,"score_gpt":0.6511159997897381,"score_spread":0.2701939192044149,"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."}}