{"id":"W4415559752","doi":"10.1111/joms.70010","title":"Categorical Atypicality and Evaluation Accuracy: Who Make More Accurate Evaluations of Atypical Firms?","year":2025,"lang":"en","type":"article","venue":"Journal of Management Studies","topic":"Auditing, Earnings Management, Governance","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute on Governance","funders":"","keywords":"Categorical variable; Earnings; Coherence (philosophical gambling strategy); Test (biology); Association (psychology)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002735134,0.000256179,0.0005944964,0.0004997477,0.0002836308,0.0001418696,0.0003894456,0.00005878112,0.00007471642],"category_scores_gemma":[0.009930301,0.000214108,0.0001581232,0.0008201943,0.0002091657,0.0007852404,0.0008779903,0.0002656044,0.00001487195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000160633,"about_ca_system_score_gemma":0.00003547633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001905154,"about_ca_topic_score_gemma":0.00002378159,"domain_scores_codex":[0.9972044,0.00007785232,0.001029889,0.0003148383,0.001091682,0.0002813992],"domain_scores_gemma":[0.98867,0.0002872373,0.009526847,0.0002873356,0.00121057,0.0000180021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006688377,0.0004652244,0.1080656,0.002818037,0.003177861,0.00005265378,0.0005723747,0.003501269,0.00003787035,0.1309645,0.07822201,0.6714538],"study_design_scores_gemma":[0.002604584,0.00004920825,0.8516156,0.0006799229,0.002213807,0.000002928884,0.003035739,0.007444299,0.0000186271,0.03215763,0.09987033,0.0003073342],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8453974,0.005648704,0.1039295,0.02559814,0.001600401,0.001744767,0.00000451691,0.00008124489,0.01599535],"genre_scores_gemma":[0.9959018,0.001210508,0.0005302369,0.001151346,0.0003246834,0.00003191355,0.000004001795,0.00001566129,0.0008298405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.74355,"threshold_uncertainty_score":0.9984095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04169986311242745,"score_gpt":0.3486549137260418,"score_spread":0.3069550506136144,"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."}}