{"id":"W4297887281","doi":"10.31234/osf.io/wdxsb","title":"Insights into accuracy of social scientists' forecasts of societal change","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Climate Change Communication and Perception","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto; University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; Agentúra na Podporu Výskumu a Vývoja; John Templeton Foundation; National Research University Higher School of Economics; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Institutes of Health; National Science Foundation","keywords":"Tournament; Benchmarking; Econometrics; Economics; Marketing; Mathematics; Business","routes":{"ca_aff":true,"ca_fund":true,"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":[0.026866,0.000642677,0.0008455156,0.003345025,0.0007395479,0.004530935,0.001050087,0.00186788,0.002689109],"category_scores_gemma":[0.1565855,0.0004871037,0.0007885003,0.002425227,0.001724655,0.006440128,0.002047766,0.001755596,0.0006146035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001316908,"about_ca_system_score_gemma":0.00103016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009983712,"about_ca_topic_score_gemma":0.008081971,"domain_scores_codex":[0.9895483,0.005176922,0.0005617887,0.00176087,0.00225594,0.000696259],"domain_scores_gemma":[0.8181841,0.147106,0.01504005,0.01100641,0.006784283,0.001879265],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009740922,0.0002558131,0.8399616,0.0001991837,0.0009013813,0.00014352,0.00575028,0.08392972,0.001633095,0.01086687,0.003963669,0.05142083],"study_design_scores_gemma":[0.0001259514,0.0003799186,0.5789288,0.0001341478,0.0002178913,0.0001247138,0.004112347,0.3401396,0.001820176,0.06946017,0.004403218,0.0001532301],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9785039,0.0004814058,0.008359056,0.003240121,0.00007131622,0.00002367758,0.001132559,0.0001320406,0.008056001],"genre_scores_gemma":[0.9980114,0.00008780388,0.001170606,0.00009965474,0.00004620188,0.000008577206,0.0004037341,0.00001415457,0.0001579156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.973134,"threshold_uncertainty_score":0.1420827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5851923084462335,"score_gpt":0.5055284926663767,"score_spread":0.07966381577985682,"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."}}