{"id":"W3012627677","doi":"10.1017/epi.2020.16","title":"Appraising the Epistemic Performance of Social Systems: The Case of Think Tank Evaluations","year":2020,"lang":"en","type":"article","venue":"Episteme","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Structuring; Situated; Epistemology; Think tanks; Sociology; Conceptual framework; Management science; Computer science; Knowledge management; Political science; Economics; Artificial intelligence; Law; Politics; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1237295,0.0008291572,0.000857937,0.005585781,0.006335634,0.01203614,0.002136268,0.004271073,0.004205044],"category_scores_gemma":[0.2398208,0.0004832966,0.0007954566,0.003175213,0.02339502,0.0148304,0.007541571,0.003522171,0.0002741547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01526769,"about_ca_system_score_gemma":0.00570893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005566922,"about_ca_topic_score_gemma":0.004886277,"domain_scores_codex":[0.8057876,0.1763318,0.002835578,0.002106889,0.009968701,0.002969391],"domain_scores_gemma":[0.6136341,0.3338516,0.01708581,0.0130192,0.01954042,0.002868766],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0008718173,0.0004913007,0.01788654,0.0009079899,0.0002666285,0.001122983,0.1036231,0.01352015,0.001523004,0.7962999,0.002867614,0.060619],"study_design_scores_gemma":[0.0003471017,0.0008723081,0.01614437,0.001773327,0.0002478571,0.0005649242,0.124742,0.05093306,0.006079726,0.7677671,0.03022565,0.0003026029],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7194859,0.001061438,0.09054597,0.01782916,0.0001926678,0.0005749571,0.00008591176,0.0001331149,0.170091],"genre_scores_gemma":[0.993139,0.00006440125,0.006111203,0.00010081,0.0000131107,0.00008294488,0.00000781676,0.00001444433,0.0004661884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8762705,"threshold_uncertainty_score":0.6543517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.089840142278987,"score_gpt":0.376799460441246,"score_spread":0.2869593181622589,"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."}}