{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001123814,0.00008473548,0.0002100826,0.00001462877,0.001088837,0.00003461753,0.0003210001,0.00004490788,0.00003068606],"category_scores_gemma":[0.0001340711,0.00005584765,0.00008894718,0.0002035083,0.0008288702,0.00009719603,0.00009442981,0.0001079562,0.00001576422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009701499,"about_ca_system_score_gemma":0.0001113204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002474619,"about_ca_topic_score_gemma":0.0004173483,"domain_scores_codex":[0.998765,0.0003430538,0.0003988375,0.0001329646,0.0001980455,0.000162095],"domain_scores_gemma":[0.9991303,0.000244493,0.0003276697,0.0001511328,0.0001130693,0.00003331323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004912091,0.00008719579,0.01001507,0.0002579245,0.0001488357,0.00001576053,0.6554943,0.0003461548,0.007050368,0.3216211,0.00284005,0.002074104],"study_design_scores_gemma":[0.0012168,0.0004451881,0.007350062,0.0002100159,0.000416045,0.00007394011,0.9601552,0.009604762,0.004351892,0.001026371,0.01445526,0.0006944919],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9675678,0.0008894465,0.00001091732,0.01128334,0.0002748542,0.0005125517,0.00002446542,0.00002004026,0.01941656],"genre_scores_gemma":[0.9994109,0.00003220877,0.00003093707,0.00009505945,0.0001949712,0.00003228318,0.000001191805,0.000008130425,0.0001942912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3205947,"threshold_uncertainty_score":0.8374564,"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."}}