{"id":"W2951278380","doi":"10.48550/arxiv.1206.3261","title":"Learning When to Take Advice: A Statistical Test for Achieving A\\n Correlated Equilibrium","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Advice (programming); Mediator; Test (biology); Computer science; Relation (database); Limit (mathematics); Artificial intelligence; Machine learning; Mathematics; Data mining; Medicine","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002027465,0.0003296619,0.0004956345,0.0003486671,0.0003264538,0.0002295234,0.001626192,0.0003327944,0.0009182019],"category_scores_gemma":[0.004465248,0.0003339769,0.0002225302,0.0007000463,0.0001696429,0.0002586869,0.001490933,0.0008082933,0.001757522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001289458,"about_ca_system_score_gemma":0.0001574909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004014113,"about_ca_topic_score_gemma":0.00002287993,"domain_scores_codex":[0.9971506,0.0003065314,0.0004882368,0.001238057,0.0002468986,0.0005696918],"domain_scores_gemma":[0.9922129,0.005354646,0.000415765,0.0010863,0.000444766,0.0004856167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000748765,0.0007658011,0.05699402,0.0001385056,0.0002266425,0.00008013735,0.004097958,0.4318474,0.002773068,0.4676412,0.02216613,0.01252035],"study_design_scores_gemma":[0.001465703,0.0004400301,0.01832529,0.0002341096,0.0006144525,0.00001385844,0.003088787,0.3191449,0.0001904365,0.5675693,0.08711837,0.001794781],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4515531,0.00002601932,0.5395204,0.000310916,0.0004091543,0.0008511638,0.0003007538,0.0002569554,0.006771453],"genre_scores_gemma":[0.9745378,0.000004142179,0.003200357,0.0001204502,0.0001541744,0.000009354062,0.00008163337,0.00003488068,0.02185719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5363201,"threshold_uncertainty_score":0.9999951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1742087542737478,"score_gpt":0.2909269082373416,"score_spread":0.1167181539635939,"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."}}