{"id":"W4366679995","doi":"10.2308/issues-2023-013","title":"The ChatGPT Artificial Intelligence Chatbot: How Well Does It Answer Accounting Assessment Questions?","year":2023,"lang":"en","type":"article","venue":"Issues in Accounting Education","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":116,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Lethbridge; Simon Fraser University; York University; University of Waterloo","funders":"","keywords":"Chatbot; Accounting; Artificial intelligence; Psychology; Computer science; Natural language processing; Economics","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002123794,0.0003601171,0.0002788974,0.0007486308,0.0007795315,0.003799512,0.0007970508,0.0001542075,0.00009845063],"category_scores_gemma":[0.001449932,0.0002880962,0.00009824838,0.002516858,0.0001756585,0.003838122,0.0003746952,0.0004457762,0.001345004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002409981,"about_ca_system_score_gemma":0.0001610278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001095225,"about_ca_topic_score_gemma":0.001261735,"domain_scores_codex":[0.9972739,0.00002664503,0.0006679505,0.0006666224,0.0005966856,0.0007681646],"domain_scores_gemma":[0.998103,0.000286797,0.0005945014,0.0005659172,0.000433212,0.0000165607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004528945,0.0006051409,0.1705681,0.0006855987,0.0000476936,0.0000157981,0.001019712,0.000476047,0.001548746,0.4134665,0.06659498,0.3449264],"study_design_scores_gemma":[0.00009915874,0.00001285507,0.07806633,0.0009294527,0.00003562183,0.000003621381,0.01207936,0.01929894,0.0007449372,0.08887343,0.798968,0.0008883199],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8897927,0.0004880102,0.001283008,0.06359023,0.01116316,0.001242976,0.000005321059,0.001055791,0.03137877],"genre_scores_gemma":[0.9896834,0.0001974613,0.0004681717,0.0009186737,0.003951688,0.0002497357,0.00007817146,0.00007605401,0.004376651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.732373,"threshold_uncertainty_score":0.9999571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02386223943037252,"score_gpt":0.323579053659364,"score_spread":0.2997168142289914,"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."}}