{"id":"W3012963710","doi":"10.1162/rest_a_01259","title":"Public Leaderboard Feedback in Sampling Competition: An Experimental Investigation","year":2022,"lang":"en","type":"article","venue":"The Review of Economics and Statistics","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"CONTEST; Competition (biology); Sampling (signal processing); Value (mathematics); Affect (linguistics); Computer science; Test (biology); Sample (material); Microeconomics; Econometrics; Economics; Mathematical economics; Psychology; Political science; Machine learning; Telecommunications; Communication","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":[],"consensus_categories":[],"category_scores_codex":[0.00993285,0.001111889,0.001197068,0.0004563713,0.001092543,0.001641264,0.002102172,0.001689603,0.01052883],"category_scores_gemma":[0.03283924,0.0004997636,0.0005576188,0.0005651534,0.002391854,0.001492109,0.001601202,0.002200762,0.0008053554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111713,"about_ca_system_score_gemma":0.001285878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009554033,"about_ca_topic_score_gemma":0.0009475811,"domain_scores_codex":[0.9939691,0.003327681,0.0003178084,0.0007669433,0.001148139,0.0004703882],"domain_scores_gemma":[0.9212528,0.05818294,0.009171213,0.007239448,0.001784332,0.002369139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.1264005,0.3186485,0.07582518,0.004492459,0.001575211,0.001772729,0.008149144,0.05036644,0.1363157,0.1149306,0.00910676,0.1524168],"study_design_scores_gemma":[0.04071426,0.3050732,0.1180046,0.0005716921,0.001676906,0.001212117,0.005422088,0.2828919,0.06908938,0.1568981,0.01769389,0.0007517919],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911401,0.00008152256,0.004291685,0.0001703928,0.00006216981,0.000464829,0.00009679788,0.00003330281,0.003659351],"genre_scores_gemma":[0.9919924,0.00007097634,0.005315398,0.0001513831,0.00006298327,0.0007866917,0.00009210862,0.00001591199,0.001512181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01052883,"threshold_uncertainty_score":0.05253053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1816447921972595,"score_gpt":0.3602538113614887,"score_spread":0.1786090191642291,"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."}}