{"id":"W7125818289","doi":"10.53106/256299802025120701002","title":"Text Mining and Machine Learning on 10-K Risk Factors and Net Income: Evidence from Apple","year":2025,"lang":"","type":"article","venue":"International Journal of Computer Auditing","topic":"Auditing, Earnings Management, Governance","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Audit; Sentiment analysis; Predictive analytics; Empirical research; Factor (programming language); Style (visual arts); Text mining; Analytics; Information extraction","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.003300437,0.0001811837,0.0002279765,0.001473778,0.0005489602,0.001814913,0.0004691627,0.0004981419,0.002257275],"category_scores_gemma":[0.02722482,0.0001468681,0.0003333404,0.002000808,0.0006896181,0.001636544,0.0007286459,0.000606373,0.0006610703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004750351,"about_ca_system_score_gemma":0.0006436442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005582757,"about_ca_topic_score_gemma":0.0079107,"domain_scores_codex":[0.9985396,0.0005292863,0.0001539187,0.000218109,0.0004665712,0.00009246911],"domain_scores_gemma":[0.9596679,0.03031336,0.005667831,0.001504186,0.002238138,0.0006085432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004197473,0.0003006531,0.9284041,0.0001331311,0.0001217307,0.0005141063,0.00185178,0.0008123544,0.0003673621,0.001064538,0.002943371,0.06306715],"study_design_scores_gemma":[0.00002455335,0.0001277256,0.9837213,0.0001488862,0.0000837679,0.0002787503,0.001723466,0.005102653,0.0006727638,0.002174774,0.005917198,0.00002417822],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994379,0.0005833163,0.0005469277,0.0007799935,0.00001186747,0.00001328249,0.0008093684,0.00002871309,0.002847596],"genre_scores_gemma":[0.9958021,0.0005685844,0.00104377,0.0001183863,0.00003425646,0.00001213648,0.00123427,0.00001378094,0.001172714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005582757,"threshold_uncertainty_score":0.01745462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01160616032608907,"score_gpt":0.2368689427741411,"score_spread":0.225262782448052,"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."}}