{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01695629,0.0006526703,0.0006343963,0.002570038,0.000744656,0.001841684,0.002261808,0.001487403,0.003973104],"category_scores_gemma":[0.1989985,0.0005925357,0.001060006,0.002127088,0.002550806,0.00499492,0.001951228,0.003301944,0.0003190572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001436972,"about_ca_system_score_gemma":0.001505878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004429474,"about_ca_topic_score_gemma":0.005057529,"domain_scores_codex":[0.9918051,0.00378578,0.0005739023,0.001198744,0.002007605,0.0006289172],"domain_scores_gemma":[0.6465393,0.3135945,0.01279808,0.01586911,0.009578189,0.001620895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002053113,0.001798265,0.5734918,0.0008286069,0.0005984784,0.0008061682,0.002608517,0.1114868,0.003203889,0.1023145,0.009200912,0.1916091],"study_design_scores_gemma":[0.0001702451,0.0003113551,0.0883484,0.0001605472,0.0002725305,0.0005036014,0.001024564,0.7842123,0.002851062,0.1202743,0.001812422,0.00005877943],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556277,0.0007698641,0.03878034,0.001022229,0.00003323552,0.00004495454,0.0005692648,0.0004467889,0.002705563],"genre_scores_gemma":[0.9937314,0.00006858527,0.005346811,0.00005505618,0.00001193775,0.0000185906,0.0004190253,0.00006211818,0.0002863951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01695629,"threshold_uncertainty_score":0.08967447,"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."}}