{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02749644,0.0006961249,0.000661357,0.001802257,0.002173162,0.004107321,0.001782125,0.001896041,0.003634852],"category_scores_gemma":[0.1131124,0.0004849464,0.0004541492,0.001333747,0.004242002,0.005735609,0.005793245,0.002305151,0.0006642513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001925877,"about_ca_system_score_gemma":0.001778104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002261592,"about_ca_topic_score_gemma":0.003163882,"domain_scores_codex":[0.9709123,0.02512807,0.0006268008,0.001178052,0.001379123,0.000775429],"domain_scores_gemma":[0.8364906,0.1470837,0.004286979,0.00524475,0.004493156,0.002400831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005948404,0.001616732,0.02757168,0.001276449,0.00005583349,0.002231206,0.8767273,0.001539349,0.00823717,0.005426957,0.00221017,0.0725123],"study_design_scores_gemma":[0.0004820304,0.004301343,0.07338276,0.001368246,0.0002438437,0.00327925,0.8235641,0.01991628,0.008680901,0.01164701,0.05276836,0.0003659396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836708,0.0001202175,0.006818258,0.0006465938,0.00003727487,0.000402159,0.00007012139,0.0001419453,0.008092677],"genre_scores_gemma":[0.9840499,0.0001367944,0.01282279,0.0003610819,0.00003292013,0.0006515927,0.0000978032,0.00005966332,0.001787407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02749644,"threshold_uncertainty_score":0.1454168,"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."}}