{"id":"W2593998405","doi":"10.1257/aer.20170299","title":"Evaluating Strategic Forecasters","year":2018,"lang":"en","type":"article","venue":"American Economic Review","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generality; Robustness (evolution); Economics; Principal (computer security); Quality (philosophy); Mechanism design; Microeconomics; Econometrics; Simple (philosophy); Computer science; Mathematical economics; Computer security","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":[0.02586365,0.0009320643,0.001720219,0.001083765,0.0006491693,0.004075849,0.001680019,0.003450701,0.00582858],"category_scores_gemma":[0.1234306,0.0005697673,0.0005132388,0.001135516,0.002559249,0.005863576,0.001434471,0.002108497,0.0006734959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002628827,"about_ca_system_score_gemma":0.002723268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001115753,"about_ca_topic_score_gemma":0.0008587921,"domain_scores_codex":[0.9881582,0.008206596,0.0004950544,0.001436978,0.001004948,0.0006982471],"domain_scores_gemma":[0.9460796,0.03593007,0.00991376,0.003672202,0.00296236,0.00144202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001229639,0.0004801688,0.02620186,0.000489766,0.0004883935,0.0002436658,0.0006112022,0.1904982,0.002086548,0.5595679,0.008287024,0.2098157],"study_design_scores_gemma":[0.0005238219,0.0009422065,0.007033803,0.0002634391,0.0001734725,0.0002053167,0.0005135592,0.2945345,0.002556719,0.68512,0.008037249,0.000095961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3713402,0.003160977,0.5523142,0.02998347,0.0006538198,0.0005787092,0.0004629693,0.0004054839,0.04110017],"genre_scores_gemma":[0.9608779,0.000570374,0.03480478,0.000451899,0.0001235752,0.000112757,0.00006025166,0.00001966443,0.002978742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02586365,"threshold_uncertainty_score":0.1367817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4133607625397049,"score_gpt":0.5322415473275208,"score_spread":0.1188807847878159,"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."}}