{"id":"W4407601102","doi":"10.2139/ssrn.5139167","title":"Empirical Deduction and Analysis of Bug Evolution in Deep Learning and Non-Deep Learning Frameworks","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Machine learning; Natural language processing","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00294065,0.0002437388,0.0005171528,0.001378688,0.0002645433,0.0002159214,0.0004401858,0.0005268878,0.000004268948],"category_scores_gemma":[0.0005219918,0.0002467693,0.0001376141,0.001204757,0.00006541301,0.0002663608,0.0005363299,0.01133967,9.069062e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007179299,"about_ca_system_score_gemma":0.0007689958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002769438,"about_ca_topic_score_gemma":0.0007701729,"domain_scores_codex":[0.9969457,0.0006116552,0.0005604551,0.0006457609,0.0003259919,0.0009103745],"domain_scores_gemma":[0.9986362,0.0002133147,0.0006272846,0.0002983305,0.0001433479,0.00008152721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004281981,0.00007558519,0.6132944,0.00007887364,0.0007274502,0.000002233867,0.001795418,0.0871591,0.0000853814,0.01733088,0.000002561306,0.2794053],"study_design_scores_gemma":[0.0002451663,0.0001279937,0.2673515,0.0001104008,0.0002939736,0.00004101652,0.0006972845,0.6987634,0.000002962794,0.0320356,0.0001179062,0.0002127535],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2089486,0.005448755,0.7845006,0.0006826257,0.0001407322,0.00008560894,6.459138e-7,0.00004026186,0.0001521636],"genre_scores_gemma":[0.9870759,0.008599645,0.003932334,0.00001690418,0.00008634378,0.000007730372,0.00004084469,0.000009441106,0.0002308066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7805682,"threshold_uncertainty_score":0.9999985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007618788415341462,"score_gpt":0.291974656129886,"score_spread":0.2843558677145446,"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."}}