{"id":"W7125897131","doi":"10.1109/smc58881.2025.11343571","title":"Can AlphaZero Master Human Concepts in Tic-Tac-Toe?","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Hierarchy; Simple (philosophy); Key (lock); Training (meteorology)","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007161097,0.0005101999,0.000600385,0.0005847222,0.0003353998,0.0007759617,0.002582439,0.0003081898,0.002141643],"category_scores_gemma":[0.0001625284,0.0005230013,0.0001875682,0.001762672,0.0006779387,0.000678448,0.001299908,0.0006031118,0.000809653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003373109,"about_ca_system_score_gemma":0.0005076923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002622137,"about_ca_topic_score_gemma":0.008321395,"domain_scores_codex":[0.9952756,0.0003154672,0.001369248,0.001329281,0.0005369347,0.001173459],"domain_scores_gemma":[0.9974858,0.0003165979,0.0001933403,0.001534026,0.0002467457,0.0002235397],"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":[0.00002228004,0.0004727335,0.02438119,0.00008906163,0.00007426889,0.0001706513,0.01153695,0.0006478578,0.002539373,0.6292341,0.01088633,0.3199452],"study_design_scores_gemma":[0.001356017,0.0008960294,0.02128107,0.001851014,0.0001050422,0.00002193522,0.006088072,0.4328793,0.2201614,0.2476238,0.06454504,0.003191228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2698162,0.00129905,0.3551834,0.03210702,0.007754662,0.001830656,0.00001197076,0.0004292412,0.3315679],"genre_scores_gemma":[0.9251836,0.00003200769,0.002677974,0.004104061,0.0001314887,0.00003492371,0.000001738525,0.00001988052,0.06781433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6553674,"threshold_uncertainty_score":0.9999683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05443323962019618,"score_gpt":0.3506640005340873,"score_spread":0.2962307609138911,"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."}}