{"id":"W4289356281","doi":"10.1007/978-3-031-11488-5_13","title":"On the Road to Perfection? Evaluating Leela Chess Zero Against Endgame Tablebases","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Chess endgame; Heuristics; Computer science; Zero (linguistics); Perfection; Artificial intelligence; Epistemology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003620025,0.0007501006,0.0008556442,0.0009159741,0.0006374865,0.003248907,0.001219387,0.001267449,0.01544382],"category_scores_gemma":[0.02578237,0.0002735015,0.0002641079,0.0004496188,0.0007095633,0.003812114,0.00164296,0.001482413,0.002051895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262371,"about_ca_system_score_gemma":0.001106823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009765313,"about_ca_topic_score_gemma":0.0199002,"domain_scores_codex":[0.9978611,0.0009243278,0.0001296659,0.00032525,0.0005943843,0.000165309],"domain_scores_gemma":[0.9906908,0.006843515,0.0003549856,0.000647774,0.0009501179,0.0005127912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009217362,0.001100877,0.04384914,0.0008374446,0.000434521,0.0002306965,0.0007876335,0.1255576,0.007453499,0.06060158,0.1226153,0.6273143],"study_design_scores_gemma":[0.000625287,0.002767327,0.02368288,0.0003356228,0.0001788026,0.0002239667,0.001358969,0.8699946,0.0104371,0.05749062,0.03281711,0.00008769718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8393385,0.003345561,0.04298833,0.003730764,0.0008409071,0.000214499,0.002369432,0.003064244,0.1041079],"genre_scores_gemma":[0.9714267,0.0001512764,0.01502823,0.0002069077,0.00004670669,0.00003206928,0.001860466,0.000175155,0.01107252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01544382,"threshold_uncertainty_score":0.05166477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05198616385661934,"score_gpt":0.3093362363009957,"score_spread":0.2573500724443763,"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."}}