{"id":"W4366231507","doi":"10.5281/zenodo.7839032","title":"What Causes Exceptions in Machine Learning Applications? Mining Machine Learning-Related Stack Traces on Stack Overflow","year":2023,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Stack (abstract data type); Computer science; Call stack; Artificial intelligence; Machine learning; 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":[0.002378314,0.0006719771,0.0006394492,0.003479196,0.001109164,0.002347726,0.0009266351,0.001301865,0.001030796],"category_scores_gemma":[0.03853538,0.0005216965,0.0008302032,0.002986271,0.001082318,0.004342563,0.001105029,0.001916829,0.0003974608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000970459,"about_ca_system_score_gemma":0.002719463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009873178,"about_ca_topic_score_gemma":0.01401067,"domain_scores_codex":[0.9972808,0.0003841632,0.0002939729,0.0006560492,0.001000589,0.0003843512],"domain_scores_gemma":[0.9680035,0.01943528,0.004367719,0.003420729,0.00365163,0.001121088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007081561,0.0004922759,0.7038518,0.0005193751,0.0002258684,0.002343524,0.001949821,0.01878559,0.01608453,0.007550722,0.01227867,0.2352096],"study_design_scores_gemma":[0.00006576742,0.0004132834,0.3348673,0.0005874981,0.0004037472,0.002863305,0.003908854,0.5204861,0.05357094,0.0646451,0.01799696,0.0001912423],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9352884,0.001179863,0.05145316,0.00232035,0.0001542444,0.0001022115,0.004015,0.003363116,0.002123749],"genre_scores_gemma":[0.9727966,0.0004153546,0.02163337,0.0003084676,0.00008416667,0.0000472411,0.003075009,0.0004607316,0.001179075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009873178,"threshold_uncertainty_score":0.01963145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01648883634158043,"score_gpt":0.2529274777351662,"score_spread":0.2364386413935858,"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."}}