{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00139489,0.000552828,0.0006982998,0.0009622736,0.0005415086,0.002055503,0.0009718755,0.0001281207,0.0004586437],"category_scores_gemma":[0.01115716,0.0005354286,0.0002011671,0.0004150334,0.0001645743,0.002253906,0.001763716,0.001068168,0.00002946018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001956453,"about_ca_system_score_gemma":0.00006380959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007244156,"about_ca_topic_score_gemma":0.00004911497,"domain_scores_codex":[0.9962596,0.0001489673,0.001374302,0.0006453011,0.001138656,0.0004331367],"domain_scores_gemma":[0.97093,0.002269362,0.02575288,0.0001843242,0.0008036024,0.00005981374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002076762,0.00006133148,0.6187968,0.0001322871,0.0008351436,0.0001216009,0.0005981,0.007412464,0.0000505574,0.0002686548,0.00308084,0.3684346],"study_design_scores_gemma":[0.002796822,0.0002090599,0.6009777,0.01346576,0.0005363744,0.00002565211,0.0006843647,0.2485356,0.0001145019,0.0009019334,0.1309604,0.0007918599],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7233859,0.001791022,0.2701733,0.001522517,0.002276297,0.0001470771,0.00002250827,0.0000395166,0.0006418073],"genre_scores_gemma":[0.9895641,0.00131096,0.003703066,0.000842322,0.003887494,0.000002315604,0.00002110084,0.0000484327,0.0006202599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3676427,"threshold_uncertainty_score":0.9997097,"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."}}