{"id":"W2772485723","doi":"10.1111/1911-3838.12150","title":"Can Language Predict Bankruptcy? The Explanatory Power of Tone in 10‐K Filings","year":2017,"lang":"en","type":"article","venue":"Accounting Perspectives","topic":"Corporate Finance and Governance","field":"Business, Management and Accounting","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bankruptcy; Explanatory power; Business; Propensity score matching; Predictive power; Actuarial science; Sample (material); Accounting; Logistic regression; Bankruptcy prediction; Logit; Matching (statistics); Going concern; Finance; Economics; Econometrics; Computer science; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004407947,0.000162347,0.000216255,0.0001103156,0.0003174738,0.0002458777,0.0006657986,0.00005693721,0.0004449885],"category_scores_gemma":[0.0005883856,0.0001275555,0.00007659881,0.0001791809,0.0002053621,0.001171993,0.0002006598,0.0001795023,0.00005284547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004253866,"about_ca_system_score_gemma":0.00003803427,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006881989,"about_ca_topic_score_gemma":0.001829237,"domain_scores_codex":[0.9989436,0.000006830547,0.0002254916,0.0002999454,0.0002586821,0.0002654254],"domain_scores_gemma":[0.9985368,0.00004889992,0.0006256193,0.0006201846,0.0001629936,0.000005466208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001328886,0.0002014187,0.9517303,0.0001388874,0.00005761279,0.0000713561,0.009538351,0.00004772102,0.001767995,0.01999974,0.01392207,0.00239166],"study_design_scores_gemma":[0.0005139361,0.000008274154,0.9751093,0.0001279593,0.00001777987,0.000001135073,0.01288036,0.0001358427,0.0001584568,0.0005354676,0.01031922,0.0001922767],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9724264,0.0004990891,0.000005587494,0.001849326,0.00019855,0.0001580966,0.0000126565,0.0000405194,0.02480975],"genre_scores_gemma":[0.9980907,0.00002379343,0.00002074418,0.0003048768,0.0004693866,0.00001431653,0.000003432696,0.0000217621,0.001051006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02566426,"threshold_uncertainty_score":0.9997312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01080263123667713,"score_gpt":0.2444816835101202,"score_spread":0.2336790522734431,"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."}}