{"id":"W3175400448","doi":"10.1609/aaai.v35i17.17830","title":"Random Forests for Opponent Hand Estimation in Gin Rummy","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Heuristics; Random forest; Adversary; Computer science; Artificial intelligence; Simple (philosophy); Machine learning; Classifier (UML); Fictitious play; Game theory; Mathematics; Computer security; Mathematical 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":[0.0008718442,0.000277282,0.0004036257,0.0001977519,0.0002465578,0.0005122896,0.001761371,0.0001348671,0.0000513925],"category_scores_gemma":[0.001947526,0.0002295044,0.00019712,0.0009371146,0.0003380546,0.0006356087,0.0004019622,0.0002784641,0.00006189335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009544789,"about_ca_system_score_gemma":0.0002570329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006382984,"about_ca_topic_score_gemma":0.0002745339,"domain_scores_codex":[0.9973035,0.00003545971,0.000917137,0.0006996449,0.0005412109,0.0005030845],"domain_scores_gemma":[0.9976192,0.0003984258,0.0004081122,0.0004295634,0.00104186,0.0001028563],"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":[0.0001703971,0.0002626214,0.0006159346,0.00006805934,0.00001552451,0.000002213499,0.002033339,0.002541357,0.03924706,0.820271,0.0001838835,0.1345886],"study_design_scores_gemma":[0.00004433238,0.00007341795,0.0001854222,0.0001870292,0.000006112461,0.000004074876,0.0002798657,0.2761118,0.4820485,0.2408337,0.0000790437,0.0001466551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2329946,0.00008826919,0.7512802,0.01030578,0.0009874367,0.0012318,0.00001031597,0.00009895011,0.003002667],"genre_scores_gemma":[0.9816601,0.00003144102,0.01760347,0.0002028673,0.00005493446,0.0001413192,0.000001693736,0.00001726415,0.0002869636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7486655,"threshold_uncertainty_score":0.9358916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08798144882918432,"score_gpt":0.3247633091335472,"score_spread":0.2367818603043629,"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."}}