{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004923074,0.0003995712,0.0003512103,0.0005957116,0.0001664982,0.000850452,0.0007776772,0.0001896265,0.00007296541],"category_scores_gemma":[0.0006198529,0.0003993716,0.0001142754,0.001550413,0.00003969088,0.001450268,0.0003768023,0.001278394,0.0001330521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002623602,"about_ca_system_score_gemma":0.0000622278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004715831,"about_ca_topic_score_gemma":0.00002199466,"domain_scores_codex":[0.9975033,0.0001068412,0.0005227478,0.0008673525,0.000435331,0.0005644743],"domain_scores_gemma":[0.9979958,0.001149208,0.00007684889,0.0005626863,0.00004060688,0.0001748523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003159789,0.000579338,0.2171003,0.000656291,0.0002812478,0.0006101684,0.01007492,0.5154271,0.0009364777,0.003524608,0.004031184,0.2467468],"study_design_scores_gemma":[0.0003958895,0.000420765,0.01418681,0.001244349,0.00002722441,0.00006745569,0.00009072227,0.8289036,0.0007845036,0.0003615389,0.1524886,0.001028534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1499998,0.004926475,0.8350209,0.0009456566,0.0006464844,0.0004855872,0.00003850258,0.007865048,0.0000715794],"genre_scores_gemma":[0.8932597,0.0007070199,0.1042256,0.000128775,0.0001532968,0.0002840103,0.0002418904,0.0001332957,0.0008664759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7432599,"threshold_uncertainty_score":0.9998458,"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."}}