{"id":"W2904526711","doi":"10.1609/aaai.v33i01.33011158","title":"Improving Search with Supervised Learning in Trick-Based Card Games","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Sampling (signal processing); Artificial intelligence; Machine learning; Focus (optics); Monte Carlo tree search; Sample (material); Sampling bias; Process (computing); Monte Carlo method; Sample size determination; Statistics; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.001130356,0.0003751452,0.0004858451,0.0004442265,0.0001749519,0.0004304876,0.002940538,0.0001505713,0.0001050049],"category_scores_gemma":[0.000472837,0.0002746684,0.0001539988,0.001848933,0.0003582387,0.0007384504,0.0004507455,0.0008730014,0.000245622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001373117,"about_ca_system_score_gemma":0.0004244349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004056739,"about_ca_topic_score_gemma":0.00006803295,"domain_scores_codex":[0.9964588,0.00006900472,0.0007923724,0.0009262566,0.001011993,0.0007415875],"domain_scores_gemma":[0.9977589,0.000334018,0.0003773932,0.0005468231,0.0008538963,0.0001289821],"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":[0.0004778474,0.0004196602,0.03568533,0.0002314384,0.00002977473,0.000006133763,0.005898376,0.01638174,0.1350166,0.455708,0.00002336229,0.3501217],"study_design_scores_gemma":[0.000052191,0.0005021255,0.0005166485,0.0003199878,0.00000641415,0.000002935066,0.0018715,0.4412787,0.5492389,0.005863366,0.0000368557,0.0003103977],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9476017,0.00003090697,0.04013531,0.00251761,0.0003493294,0.001055327,0.000001898852,0.0002073643,0.008100499],"genre_scores_gemma":[0.9940047,0.00001177041,0.005250231,0.0001730036,0.00004233655,0.00004293849,5.03427e-7,0.00002970451,0.0004448449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4498447,"threshold_uncertainty_score":0.9999706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05390015759600682,"score_gpt":0.281418344109766,"score_spread":0.2275181865137592,"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."}}