{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007358448,0.0007164658,0.0008521589,0.001850805,0.0005302388,0.00183991,0.001352799,0.001509451,0.00703179],"category_scores_gemma":[0.04995149,0.0002717377,0.0003311893,0.00142311,0.0005884233,0.00227908,0.001889218,0.00100807,0.004157574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101987,"about_ca_system_score_gemma":0.0008673514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004615243,"about_ca_topic_score_gemma":0.005238126,"domain_scores_codex":[0.993454,0.004026881,0.0003292577,0.0006784138,0.001174544,0.000336969],"domain_scores_gemma":[0.9428097,0.04523946,0.002775704,0.00284362,0.003800517,0.002530981],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.008923301,0.003993085,0.2272876,0.001828887,0.0003923438,0.001045946,0.008220077,0.01874761,0.01797159,0.003513211,0.1108926,0.5971838],"study_design_scores_gemma":[0.00135386,0.009170501,0.3547557,0.0007752654,0.0003913262,0.001554341,0.008343135,0.4951406,0.03344813,0.01076318,0.08359013,0.0007138391],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.94031,0.0005633372,0.02304358,0.001521223,0.0002546281,0.000699421,0.004328985,0.01610966,0.01316914],"genre_scores_gemma":[0.9653708,0.0001433752,0.02249816,0.0006388068,0.00007876631,0.0005595514,0.004287094,0.0003957136,0.006027735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9926416,"threshold_uncertainty_score":0.03891563,"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."}}