{"id":"W4403184883","doi":"10.1080/2331186x.2024.2412492","title":"Exploring ChatGPT’s capabilities in solving accounting standards problems: the case of IAS 37","year":2024,"lang":"en","type":"article","venue":"Cogent Education","topic":"Impact of AI and Big Data on Business and Society","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Canadian Intensive Care Foundation","keywords":"Accounting; Psychology; Business","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003905249,0.00008730382,0.0001341907,0.0001326356,0.0001599775,0.0004419919,0.0002355005,0.00003170025,0.0001475009],"category_scores_gemma":[0.001390869,0.00005169944,0.0000755286,0.000765322,0.00007093517,0.001049613,0.00006983512,0.0001059122,0.0000111044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001249338,"about_ca_system_score_gemma":0.0007213825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006816962,"about_ca_topic_score_gemma":0.0001414485,"domain_scores_codex":[0.9985681,0.00006781823,0.0004286437,0.0002318849,0.0005360139,0.0001675577],"domain_scores_gemma":[0.9987188,0.000433711,0.00009469104,0.0003101742,0.0004103892,0.0000322314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001333956,0.000215292,0.01280444,0.0003919568,0.00002679124,0.00002424399,0.1161416,0.0002187543,0.001400848,0.01170279,0.01212955,0.8449304],"study_design_scores_gemma":[0.0004226732,0.0001229194,0.05167795,0.001919358,0.00007259455,0.0003987256,0.6228228,0.009149707,0.005366369,0.03175863,0.2755996,0.0006887259],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922889,0.002797478,0.0003603532,0.00202515,0.00171976,0.0001859697,0.0000426064,0.0000178717,0.0005618412],"genre_scores_gemma":[0.999122,0.0002768094,0.00005893044,0.00007439966,0.000207132,0.00004794067,0.000007219714,0.000006919657,0.0001986557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8442416,"threshold_uncertainty_score":0.4262138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2401344037900175,"score_gpt":0.4076813742910712,"score_spread":0.1675469705010537,"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."}}