{"id":"W3162341794","doi":"10.2139/ssrn.2716166","title":"Classifying Restatements: An Application of Machine Learning and Textual Analytics","year":2019,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Auditing, Earnings Management, Governance","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Analytics; Computer science; Artificial intelligence; Data science; Natural language processing; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.002391138,0.0009758008,0.0006844844,0.00993997,0.0008545496,0.002530235,0.001291943,0.001018693,0.005191319],"category_scores_gemma":[0.01230472,0.0002093335,0.0009039044,0.00510595,0.0004495112,0.002981578,0.00130858,0.0008530806,0.003684483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000587206,"about_ca_system_score_gemma":0.0009633312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004339971,"about_ca_topic_score_gemma":0.004412318,"domain_scores_codex":[0.9977317,0.0004939151,0.0004154255,0.0003958638,0.0008204647,0.000142623],"domain_scores_gemma":[0.9867943,0.008173886,0.001372174,0.001081772,0.002188597,0.0003892024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001031444,0.001156748,0.05149933,0.0009856534,0.0001502534,0.00092711,0.001156742,0.006788842,0.02047768,0.004877112,0.02551828,0.8854308],"study_design_scores_gemma":[0.0001744167,0.0006862814,0.06591806,0.0003021198,0.0003344089,0.001110483,0.002743965,0.8149084,0.04686087,0.01970174,0.04707817,0.0001812203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5733976,0.002652384,0.3306956,0.001766803,0.000598656,0.001686129,0.04053697,0.02537332,0.02329255],"genre_scores_gemma":[0.6792997,0.0005847175,0.2695342,0.0001593843,0.0004281387,0.000533389,0.03991428,0.0005510632,0.008995165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00993997,"threshold_uncertainty_score":0.01736671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006933862446874895,"score_gpt":0.2332147598160206,"score_spread":0.2262808973691457,"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."}}