{"id":"W4404612850","doi":"10.1007/s43069-024-00375-z","title":"A Behavioral Test and Classification of Solution Concepts in Games","year":2024,"lang":"en","type":"article","venue":"Operations Research Forum","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Test (biology); Psychology; Computer science; Artificial intelligence","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":[0.003487648,0.000759096,0.0004426628,0.002340525,0.0006186388,0.001684888,0.00109591,0.001263983,0.007521351],"category_scores_gemma":[0.05928449,0.0001711196,0.0008431174,0.00106691,0.00163224,0.003523461,0.001357756,0.001610206,0.0006113505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008519901,"about_ca_system_score_gemma":0.001031277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002707864,"about_ca_topic_score_gemma":0.002157757,"domain_scores_codex":[0.9963807,0.001645831,0.0003903442,0.0004583877,0.0009253256,0.0001994768],"domain_scores_gemma":[0.9350724,0.05066657,0.004833437,0.003217694,0.004112264,0.002097782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006980687,0.009128994,0.4952403,0.00136165,0.0006216963,0.0002269561,0.004972221,0.01994797,0.01700443,0.1098277,0.009638214,0.3250492],"study_design_scores_gemma":[0.0009829279,0.008638028,0.4468736,0.0003979675,0.0003466638,0.0004492778,0.006543042,0.3938984,0.01236374,0.1201668,0.009159876,0.0001796694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9227818,0.0001524263,0.04322696,0.0006839123,0.00009940095,0.0009521769,0.001235636,0.0002547935,0.03061283],"genre_scores_gemma":[0.9749115,0.00005342226,0.02173514,0.0001036682,0.00002349751,0.0005560381,0.001134687,0.00003102938,0.001451151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007521351,"threshold_uncertainty_score":0.02516145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1646582393781355,"score_gpt":0.472597361497433,"score_spread":0.3079391221192976,"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."}}