{"id":"W3131451649","doi":"10.2308/isys-19-003","title":"Classifying Restatements: An Application of Machine Learning and Textual Analytics","year":2021,"lang":"en","type":"article","venue":"Journal of Information Systems","topic":"Auditing, Earnings Management, Governance","field":"Business, Management and Accounting","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Audit; Computer science; Quality (philosophy); Artificial intelligence; Scalability; Analytics; Natural language processing; Machine learning; Data mining; Accounting; Database; Business","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":[0.001002305,0.00009748114,0.0002276871,0.000282528,0.0001061325,0.0003326689,0.0001240952,0.00002872355,0.00001459034],"category_scores_gemma":[0.00167132,0.00009012518,0.00004237398,0.0003792779,0.00002221995,0.004170529,0.00008708404,0.0001878467,0.00001883459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004684658,"about_ca_system_score_gemma":0.00002749106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001273989,"about_ca_topic_score_gemma":0.00001336207,"domain_scores_codex":[0.9983679,0.00002471992,0.0009448246,0.00006760713,0.0004783953,0.0001165312],"domain_scores_gemma":[0.9792269,0.00003172185,0.01983409,0.00009887191,0.0007919652,0.00001640415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001663019,0.000169355,0.5116024,0.004161731,0.0003840021,0.00004037054,0.001490297,0.06405389,0.002465763,0.06735035,0.002448019,0.3456675],"study_design_scores_gemma":[0.001287193,0.00005432161,0.01957651,0.0003985246,0.0001090727,0.00007486038,0.01024411,0.2094513,0.00008859664,0.00009913787,0.7583876,0.0002287429],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.227162,0.0002811847,0.7607846,0.000203806,0.0002920664,0.0001962882,0.000004577087,0.00003507562,0.01104045],"genre_scores_gemma":[0.9989068,0.00007371798,0.0004237566,0.0001483113,0.0002728445,0.000002228285,0.00003481824,0.000008304733,0.0001292033],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7717448,"threshold_uncertainty_score":0.3675199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01267990658168634,"score_gpt":0.2436106463589982,"score_spread":0.2309307397773119,"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."}}