{"id":"W2781375226","doi":"10.1109/tg.2017.2785042","title":"Move Prediction Using Deep Convolutional Neural Networks in <italic>Hex</italic>","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Games","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Deep learning; Monte Carlo tree search; Computer science; Deep neural networks; Champion; Artificial neural network; Artificial intelligence; Machine learning; Monte Carlo method; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003995913,0.0007501077,0.0003426325,0.0003019065,0.0002893131,0.0009694503,0.001002109,0.0007524238,0.01151938],"category_scores_gemma":[0.001704634,0.0004634536,0.0003956868,0.0002781256,0.0003546239,0.001370226,0.0007707065,0.001378053,0.001851863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001181414,"about_ca_system_score_gemma":0.0006550961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02226749,"about_ca_topic_score_gemma":0.03720561,"domain_scores_codex":[0.9997476,0.00004087961,0.00001015545,0.00008410059,0.00006751403,0.00004986217],"domain_scores_gemma":[0.9997582,0.00006774985,0.00001930409,0.00005319954,0.00007950783,0.00002204453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005216386,0.0003009199,0.00550404,0.0001910419,0.0001380001,0.000208599,0.00009850205,0.5773532,0.01675909,0.02422991,0.04267273,0.3320222],"study_design_scores_gemma":[0.00001512733,0.00003965461,0.001039043,0.00001674395,0.000007751807,0.00001520271,0.00001145477,0.9827285,0.006175028,0.005706587,0.004233952,0.00001094644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3272142,0.001928678,0.5807781,0.00314675,0.0009778478,0.0003129049,0.006066312,0.02219324,0.05738207],"genre_scores_gemma":[0.8170922,0.0003933594,0.1359793,0.0004361481,0.00007029774,0.0002221953,0.005939184,0.0005732041,0.03929412],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02226749,"threshold_uncertainty_score":0.04427576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03570550559570138,"score_gpt":0.2824381058683625,"score_spread":0.2467326002726611,"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."}}