{"id":"W2913781869","doi":"10.1016/j.artint.2019.103216","title":"The Hanabi challenge: A new frontier for AI research","year":2019,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; Domain (mathematical analysis); Imperfect; Artificial intelligence; Frontier; Perfect information; State (computer science); Cognitive science; Data science; Human–computer interaction; Psychology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002765794,0.000253343,0.000262685,0.000196698,0.0008912323,0.0009740415,0.003472166,0.0001591959,0.000123467],"category_scores_gemma":[0.0009832397,0.0001946937,0.0001948225,0.0009770301,0.0003808465,0.0007468685,0.0005891784,0.0005724311,0.004550911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001242969,"about_ca_system_score_gemma":0.0004391061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003982185,"about_ca_topic_score_gemma":0.0007186105,"domain_scores_codex":[0.9960883,0.0002253092,0.0007192388,0.000915184,0.0008693484,0.001182573],"domain_scores_gemma":[0.9951604,0.001989497,0.0001276239,0.001693155,0.0007774605,0.0002518506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003150698,0.00004253442,0.00002560789,0.000005404961,0.00001288802,0.000002306102,0.001264079,0.0002442219,0.0004088903,0.572634,0.007207241,0.4181213],"study_design_scores_gemma":[0.00001535025,0.0003210878,0.0000125952,0.00002486476,0.000003441431,0.00000326619,0.001098072,0.1147192,0.05819198,0.6767836,0.1485765,0.0002500766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00263411,0.0009457857,0.9543387,0.03294761,0.002969794,0.001383758,0.000002450182,0.000210242,0.004567596],"genre_scores_gemma":[0.9664052,0.0002411984,0.01938433,0.0007999935,0.000939672,0.0002081724,0.00000205841,0.00005163611,0.0119678],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.963771,"threshold_uncertainty_score":0.9962242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1628522236355365,"score_gpt":0.4126734209769778,"score_spread":0.2498211973414413,"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."}}