{"id":"W2915727719","doi":"10.1613/jair.1.11361","title":"Level-0 Models for Predicting Human Behavior in Games","year":2019,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Microsoft Research","keywords":"Computer science; Weighting; Hierarchy; Action (physics); Game theory; Variance (accounting); Artificial intelligence; Construct (python library); Mathematical economics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004704287,0.00008777333,0.0003487885,0.0008620829,0.0001056169,0.0001228901,0.0003771278,0.00008842959,0.0004580444],"category_scores_gemma":[0.0001608257,0.00008843104,0.000150363,0.000409104,0.00006886062,0.0004121025,0.0000495147,0.0004854505,0.0001032527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001398837,"about_ca_system_score_gemma":0.00007107183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002627101,"about_ca_topic_score_gemma":0.0001255649,"domain_scores_codex":[0.998005,0.00001603178,0.00119656,0.0002082808,0.0001617923,0.0004123847],"domain_scores_gemma":[0.9988536,0.0001471035,0.0003793242,0.0001972371,0.0003327137,0.00009002766],"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":[0.0002260744,0.00060888,0.2739595,0.00009524715,0.00005171403,0.00003125274,0.002076837,0.04323877,0.001255274,0.6492605,0.0003538,0.02884217],"study_design_scores_gemma":[0.0002109026,0.001311174,0.01666543,0.0001706979,0.000006249156,0.00001817917,0.002413496,0.5022576,0.004722034,0.4671908,0.004700355,0.0003330239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837366,0.0005499828,0.01249413,0.0002432089,0.0003577684,0.0003254972,0.0000270294,0.000003277854,0.002262499],"genre_scores_gemma":[0.9983213,0.000255833,0.0005168986,0.00001561715,0.0002677265,0.00001320064,0.000001779885,0.00001693648,0.0005907087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4590189,"threshold_uncertainty_score":0.5015265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.442690473713899,"score_gpt":0.4256519713124554,"score_spread":0.01703850240144361,"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."}}