{"id":"W2120292430","doi":"10.1177/1098214012440030","title":"A New Realistic Evaluation Analysis Method","year":2012,"lang":"en","type":"article","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Health Research Board","keywords":"Coding (social sciences); Computer science; Qualitative research; Qualitative analysis; Narrative; Management science; Context (archaeology); Evaluation methods; Data science; Psychology; Sociology; Social science; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.08044642,0.0001415747,0.000533049,0.001323794,0.0001095023,0.0001471727,0.0003528727,0.00003633859,0.009592068],"category_scores_gemma":[0.008161817,0.0001007493,0.000343252,0.004146119,0.00005274584,0.001195702,0.00003159003,0.0001700161,0.0001588976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003798557,"about_ca_system_score_gemma":0.001389211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001176767,"about_ca_topic_score_gemma":0.00005235481,"domain_scores_codex":[0.9862043,0.003609062,0.001451623,0.0002130883,0.008253094,0.0002688432],"domain_scores_gemma":[0.9905058,0.001539608,0.002638974,0.0004734318,0.004504244,0.0003379342],"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":[0.0000564718,0.00005386677,0.03920751,5.019984e-7,0.0002852232,2.033798e-7,0.001772269,0.04308439,0.0001658937,0.0003873015,0.003879573,0.9111068],"study_design_scores_gemma":[0.001017387,0.0004586474,0.5332966,0.00001123998,0.004213882,0.00004073945,0.003279864,0.443103,0.0001597274,0.009809973,0.004422669,0.0001862399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2729564,0.0004732068,0.7160211,0.002329892,0.0008939134,0.0003456153,0.000003462476,0.00000912737,0.006967263],"genre_scores_gemma":[0.9390099,0.00001810296,0.05985039,0.0003308245,0.0005459119,0.000008960162,0.00001233311,0.000007946536,0.0002156545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9109206,"threshold_uncertainty_score":0.9913133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2974231815816114,"score_gpt":0.6135208376358036,"score_spread":0.3160976560541922,"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."}}