{"id":"W4409053427","doi":"10.1007/978-3-031-86585-5_4","title":"Analysing KataGo: A Comparative Evaluation Against Perfect Play in the Game of Go","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Theoretical computer science","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":[0.01139073,0.001259048,0.001259791,0.00229996,0.001990196,0.004014434,0.002689084,0.002286772,0.02153835],"category_scores_gemma":[0.08608143,0.0003610663,0.0009455163,0.001756541,0.006222708,0.01021373,0.004285436,0.002898768,0.001600299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003668342,"about_ca_system_score_gemma":0.001717074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008177824,"about_ca_topic_score_gemma":0.01131858,"domain_scores_codex":[0.9883049,0.007584037,0.0005046874,0.0008420369,0.002207064,0.0005573071],"domain_scores_gemma":[0.8750946,0.113425,0.002390727,0.004437997,0.003484167,0.001167547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02113421,0.00119479,0.01156891,0.003725179,0.0005705517,0.0002226187,0.008575481,0.03502515,0.003202967,0.7125652,0.02545142,0.1767635],"study_design_scores_gemma":[0.003579831,0.008876144,0.02991167,0.001790523,0.001584368,0.0006670806,0.02360728,0.2090713,0.008155243,0.6273921,0.08503941,0.0003250988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6474516,0.004448902,0.08294664,0.005263368,0.00100698,0.0006501098,0.001513403,0.0009461479,0.2557728],"genre_scores_gemma":[0.9763155,0.0003411676,0.01468582,0.0003910986,0.00008413893,0.000236687,0.0006779525,0.0003548625,0.006912824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02153835,"threshold_uncertainty_score":0.07205296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06007977150295404,"score_gpt":0.3403553913993017,"score_spread":0.2802756198963476,"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."}}