{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001069407,0.001015544,0.001095475,0.001331244,0.0003795444,0.001997678,0.006487866,0.0005584799,0.00008132322],"category_scores_gemma":[0.0002355923,0.0008428723,0.0002757154,0.001492721,0.001461273,0.001084941,0.003130715,0.001796362,0.0004558395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006378861,"about_ca_system_score_gemma":0.001206424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006318882,"about_ca_topic_score_gemma":0.0004911417,"domain_scores_codex":[0.9929084,0.00005193338,0.001194668,0.002811851,0.001738711,0.001294423],"domain_scores_gemma":[0.9953273,0.001218697,0.0004356786,0.002290878,0.0003760475,0.0003514287],"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":[0.0000201171,0.00008940078,0.00007372199,0.0001508343,0.00004445285,0.0005996425,0.003001931,0.08246739,0.0001990261,0.03827368,0.0008505357,0.8742293],"study_design_scores_gemma":[0.00009744748,0.0003022801,0.00001402978,0.001380614,0.00002457062,0.00008588975,0.000001756747,0.82664,0.007135793,0.1443337,0.01871201,0.001271983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001714382,0.001728359,0.9797744,0.001243631,0.004935875,0.0007069662,0.00001868375,0.0006851722,0.0107355],"genre_scores_gemma":[0.4319389,0.0002980848,0.5390119,0.008254617,0.002490153,0.0001153889,0.00002773808,0.0003068056,0.01755638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8729573,"threshold_uncertainty_score":0.9994022,"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."}}