{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007511693,0.00005135673,0.0000681862,0.0003372767,0.0001336587,0.0003200716,0.000275605,0.00004735578,0.00002101154],"category_scores_gemma":[0.0002642782,0.00004758931,0.00001731676,0.0007887699,0.0002537603,0.0007528185,0.0001645582,0.0001965672,0.0000616215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007249587,"about_ca_system_score_gemma":0.0001950375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004461789,"about_ca_topic_score_gemma":0.002300819,"domain_scores_codex":[0.9988933,0.000110014,0.0002121106,0.000254198,0.0002930636,0.0002373149],"domain_scores_gemma":[0.9992705,0.0002391385,0.00000705141,0.0002465644,0.0001922053,0.0000445222],"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":[0.000003737645,0.0002476592,0.007498269,0.00003120796,0.000004458995,0.00001271778,0.005276779,0.0004322257,0.1611502,0.505264,0.002591918,0.3174868],"study_design_scores_gemma":[0.00003458361,0.0001987833,0.00492836,0.00007951116,0.000001080177,0.000005427106,0.0009813184,0.967845,0.01941188,0.003533139,0.002905422,0.00007549926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6936591,0.001769292,0.280425,0.02018578,0.0003036642,0.0008663408,0.00002200207,0.0001432524,0.002625639],"genre_scores_gemma":[0.9942029,0.00007487788,0.004997416,0.000009362294,0.00001698343,0.00007582094,0.000003827915,0.000004581414,0.0006142213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9674128,"threshold_uncertainty_score":0.3086458,"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."}}