{"id":"W4400289394","doi":"10.1007/s10664-024-10499-9","title":"What causes exceptions in machine learning applications? Mining machine learning-related stack traces on Stack Overflow","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Stack (abstract data type); Computer science; Call stack; Machine learning; Artificial intelligence; Operating system","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":[0.002710057,0.0005748275,0.0005450023,0.003387522,0.0006144731,0.001788256,0.0009512736,0.001061189,0.000674698],"category_scores_gemma":[0.05564891,0.000438409,0.0005852902,0.002878271,0.0006447666,0.003137883,0.000797621,0.001782648,0.0002814437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006176682,"about_ca_system_score_gemma":0.001777465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005450048,"about_ca_topic_score_gemma":0.006796717,"domain_scores_codex":[0.9974981,0.0004746332,0.0003037557,0.0005143114,0.0009394512,0.0002698633],"domain_scores_gemma":[0.9610206,0.02301893,0.007602537,0.003353736,0.003870252,0.001133903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004218135,0.0004264081,0.8835168,0.0002179122,0.0001969916,0.0009987882,0.001054506,0.01155076,0.00534663,0.003251977,0.002336487,0.09068097],"study_design_scores_gemma":[0.00005074772,0.0003903066,0.455402,0.0002967685,0.0003726033,0.00182446,0.002669189,0.4755221,0.01664505,0.04204547,0.00467832,0.0001029162],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857242,0.0004124818,0.01144088,0.0004827423,0.00003970042,0.00003520759,0.0007174711,0.0004348136,0.000712569],"genre_scores_gemma":[0.9940841,0.0001695735,0.004712326,0.00005926652,0.0000254177,0.00001585158,0.0006503188,0.00004739803,0.0002358221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005450048,"threshold_uncertainty_score":0.01433235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02190445434774125,"score_gpt":0.2865611999828497,"score_spread":0.2646567456351085,"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."}}