{"id":"W2153678894","doi":"","title":"Achieving master level play in 9×9 computer go","year":2008,"lang":"en","type":"article","venue":"UCL Discovery (University College London)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Heuristic; Artificial intelligence; Monte Carlo tree search; Function (biology); Value (mathematics); Tree (set theory); State (computer science); Bellman equation; Monte Carlo method; Domain (mathematical analysis); Machine learning; Algorithm; Theoretical computer science; Mathematical optimization; Mathematics; Statistics","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":[0.001183581,0.0008349498,0.0008556959,0.0005485456,0.0007374124,0.001041676,0.001333107,0.001567798,0.009666081],"category_scores_gemma":[0.003870582,0.0002935567,0.000656047,0.0003820194,0.001218584,0.001487296,0.002254543,0.001115887,0.000893329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234489,"about_ca_system_score_gemma":0.001331904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01000525,"about_ca_topic_score_gemma":0.01284306,"domain_scores_codex":[0.9993622,0.0001376207,0.00002618723,0.0001298766,0.0001254247,0.0002187198],"domain_scores_gemma":[0.9988399,0.0006800066,0.0001050818,0.0001270869,0.00007173818,0.0001761545],"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":[0.0008456086,0.0004578462,0.004059731,0.0001441411,0.00007019745,0.00038711,0.0008202732,0.8059977,0.003198024,0.07112946,0.004613389,0.1082765],"study_design_scores_gemma":[0.00009252477,0.0002296468,0.0008310394,0.00001966576,0.000009697598,0.00007715362,0.0001977011,0.9545045,0.001667669,0.03896645,0.00338842,0.00001538761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6143522,0.0001159774,0.3148961,0.000545228,0.0000479003,0.0003965911,0.0002517808,0.002912136,0.06648202],"genre_scores_gemma":[0.9135765,0.00003205499,0.07740148,0.00008599772,0.000008080999,0.0001545956,0.0002464,0.0001405563,0.008354369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01000525,"threshold_uncertainty_score":0.03233629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04533729866204827,"score_gpt":0.2195444041823804,"score_spread":0.1742071055203321,"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."}}