{"id":"W4403925054","doi":"10.1214/24-aoas1933","title":"Learning risk preferences in Markov decision processes: An application to the fourth down decision in the national football league","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Football; League; Computer science; Artificial intelligence; Econometrics; Economics; Political science","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":[0.003178391,0.0001197598,0.0001964663,0.0002804156,0.0001381091,0.0001545762,0.000540641,0.00005083769,0.00004873213],"category_scores_gemma":[0.0003073313,0.00007130031,0.00002783785,0.0007898213,0.00004981266,0.00009310881,0.00005472821,0.0002978133,0.00007764956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002233334,"about_ca_system_score_gemma":0.00006284786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003382877,"about_ca_topic_score_gemma":0.001788875,"domain_scores_codex":[0.9987256,0.00001896238,0.0005993503,0.0002903348,0.0001780782,0.0001877056],"domain_scores_gemma":[0.9984988,0.0008994298,0.0002351003,0.0002438226,0.00009392377,0.00002891648],"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":[0.0002489218,0.0001501146,0.0104872,0.00009503152,0.00003463214,0.000001603744,0.009667967,0.2539046,0.000004283998,0.4414412,0.005244355,0.2787201],"study_design_scores_gemma":[0.0001627364,0.000131624,0.09460575,0.00006194958,0.000007404969,0.000001032961,0.0007598686,0.291999,0.00001271428,0.5577046,0.05437994,0.0001733954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6617839,0.0009889831,0.3227397,0.001482771,0.0001460752,0.001008023,0.0007929504,0.00002278653,0.01103491],"genre_scores_gemma":[0.9947368,0.002194386,0.002446228,0.000360903,0.00008620872,0.00008739874,0.00004232266,0.00001277189,0.00003298056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3329529,"threshold_uncertainty_score":0.2907542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0637202319053105,"score_gpt":0.3171072281836259,"score_spread":0.2533869962783154,"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."}}