{"id":"W4403816328","doi":"10.48550/arxiv.2409.20553","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research; John D. and Catherine T. MacArthur Foundation","keywords":"Computer science; Artificial intelligence; Cognitive science; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059021,0.001183691,0.0007397216,0.0006724557,0.00054308,0.00172978,0.002867213,0.001469435,0.009002072],"category_scores_gemma":[0.003316662,0.0007220299,0.001049988,0.0004949579,0.0006441449,0.001623878,0.001497819,0.002397559,0.003556601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001476289,"about_ca_system_score_gemma":0.001561161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0175624,"about_ca_topic_score_gemma":0.02541639,"domain_scores_codex":[0.9995958,0.00007954618,0.00001799074,0.0001777898,0.00006846737,0.00006035198],"domain_scores_gemma":[0.9994441,0.0002404186,0.00004779003,0.00007702177,0.0001251374,0.00006560479],"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":[0.0003155759,0.0001736032,0.005581966,0.0001038039,0.0001439765,0.0001058551,0.0001112129,0.8746755,0.002281172,0.01443892,0.01492282,0.08714566],"study_design_scores_gemma":[0.000007865836,0.00002038624,0.0002800676,0.000005257917,0.000007038192,0.00001062227,0.000003932676,0.9944114,0.000265379,0.003943272,0.001039744,0.000005027826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07136814,0.001219951,0.8830219,0.001782522,0.0005591537,0.0003680314,0.004130554,0.01608908,0.02146065],"genre_scores_gemma":[0.724884,0.000523033,0.2395845,0.0009478268,0.0002858969,0.001144035,0.005079127,0.0008467105,0.02670492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0175624,"threshold_uncertainty_score":0.03492033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1681204725693926,"score_gpt":0.2585748532727388,"score_spread":0.09045438070334619,"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."}}