{"id":"W4392172476","doi":"10.1007/978-3-031-54968-7_3","title":"Stockfish or Leela Chess Zero? A Comparison Against Endgame Tablebases","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Chess endgame; Computer science; Zero (linguistics); Artificial intelligence; Philosophy; Linguistics","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":[0.00219623,0.0006841003,0.001358398,0.002230631,0.001012454,0.003947692,0.002579782,0.001213616,0.09782733],"category_scores_gemma":[0.01642624,0.0002728194,0.0005446281,0.001852919,0.0009472142,0.007447175,0.002670357,0.001264548,0.01009554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001402229,"about_ca_system_score_gemma":0.001546218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007451877,"about_ca_topic_score_gemma":0.01138943,"domain_scores_codex":[0.9979978,0.0004995383,0.0001059497,0.0002463152,0.0009728975,0.0001773888],"domain_scores_gemma":[0.9925624,0.004666783,0.0002412512,0.001195396,0.0007916475,0.0005425664],"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":[0.0157576,0.001543208,0.004776,0.002169421,0.0002159756,0.00008155907,0.0006490149,0.01562131,0.001548449,0.1122619,0.08610106,0.7592745],"study_design_scores_gemma":[0.006478232,0.01614937,0.03289582,0.002510995,0.001099655,0.0009412433,0.006922207,0.1819388,0.01099773,0.2157314,0.5239885,0.000346097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.362641,0.01681175,0.03961372,0.003706292,0.002087973,0.0007345926,0.009835083,0.007148066,0.5574214],"genre_scores_gemma":[0.838999,0.004724327,0.04040173,0.0008804703,0.000198197,0.0003283906,0.01138107,0.002110057,0.1009767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09782733,"threshold_uncertainty_score":0.327265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04637551862151267,"score_gpt":0.3024363546858843,"score_spread":0.2560608360643716,"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."}}