{"id":"W2155014708","doi":"10.1609/aaai.v24i1.7644","title":"Beyond Equilibrium: Predicting Human Behavior in Normal-Form Games","year":2010,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":134,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nash equilibrium; Computer science; Mathematical economics; Set (abstract data type); Range (aeronautics); Best response; Game theory; Outcome (game theory); Extensive-form game; Equilibrium selection; Repeated game; Economics","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":[0.0008202161,0.0002075384,0.0002814195,0.0001456297,0.0004755743,0.0001942441,0.001088586,0.0001546348,0.0003614884],"category_scores_gemma":[0.0003183116,0.0001839437,0.0001167347,0.0003638644,0.001149,0.0005343843,0.0003275062,0.0005555942,0.00005123376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106252,"about_ca_system_score_gemma":0.000106722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002251746,"about_ca_topic_score_gemma":0.005473426,"domain_scores_codex":[0.9980844,0.00001507482,0.0006297556,0.0003903563,0.0003818288,0.000498595],"domain_scores_gemma":[0.9990107,0.00006276008,0.0003594497,0.0001722244,0.0002859177,0.0001089522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002770267,0.0002248006,0.0912633,0.00000958559,0.000004866856,5.078243e-7,0.01225363,0.000001066855,0.3504376,0.5391585,0.00003780135,0.006580575],"study_design_scores_gemma":[0.00006181723,0.0002224223,0.01136935,0.0001144722,0.00002942072,0.000001677637,0.02469712,0.000225885,0.8679291,0.09477656,0.0001480786,0.0004240765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8847578,0.000009722206,8.915305e-7,0.0009504143,0.0005716145,0.000510361,0.000007212139,0.0000539834,0.113138],"genre_scores_gemma":[0.9988967,0.00001853092,0.0002034319,0.00006508498,0.0001548992,0.0001062001,7.168038e-7,0.00001733711,0.0005370855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5174915,"threshold_uncertainty_score":0.7501007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08053815555827337,"score_gpt":0.359902836620469,"score_spread":0.2793646810621956,"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."}}