{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007954052,0.00006777787,0.0002058942,0.00002878692,0.000428984,0.00003405222,0.0001594503,0.00001206561,0.0001700584],"category_scores_gemma":[0.00002824943,0.00006768529,0.00002108605,0.0000608884,0.0003281462,0.00012241,0.0001125071,0.00008010536,0.000002285634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001924763,"about_ca_system_score_gemma":0.00008603704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005783071,"about_ca_topic_score_gemma":0.0008222001,"domain_scores_codex":[0.9992063,0.000175998,0.0003143454,0.0001298215,0.00004788849,0.0001256409],"domain_scores_gemma":[0.9995695,0.00008707304,0.0001654024,0.0001081353,0.00001992378,0.00004990491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.000003799361,0.00005378994,0.001746646,0.0001029365,0.000006679167,2.628892e-7,0.005725148,0.00004646873,0.00003829184,0.988484,0.0001639322,0.003628068],"study_design_scores_gemma":[0.003602904,0.00186615,0.01713223,0.00195567,0.0002173862,0.00003252222,0.361338,0.005871386,0.0009200933,0.2634935,0.3408879,0.002682171],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9473423,0.04279679,0.00004807287,0.004870244,0.0002711639,0.0006211182,0.0002798588,0.00001172512,0.003758762],"genre_scores_gemma":[0.9146129,0.08018079,0.004008138,0.0009506199,0.00004504041,0.00008562539,0.00006871818,0.00001051698,0.00003766975],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7249904,"threshold_uncertainty_score":0.3299441,"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."}}