{"id":"W4389337865","doi":"10.1007/s10664-023-10400-0","title":"Bug characterization in machine learning-based systems","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; Polytechnique Montréal","funders":"","keywords":"Computer science; Software bug; Software; Component (thermodynamics); Software system; Task (project management); Process (computing); Software engineering; Software development; Focus (optics); Software maintenance; Corrective maintenance; Machine learning; Reliability engineering; Operating system; Systems engineering; Engineering; Preventive maintenance","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":[],"consensus_categories":[],"category_scores_codex":[0.0005705293,0.0002256833,0.0002546618,0.0007104835,0.00006223193,0.0001801854,0.0006534284,0.0001284828,0.000009783492],"category_scores_gemma":[0.002826751,0.0002373107,0.00006381487,0.00280623,0.00001194978,0.000303428,0.0002245215,0.0005310088,0.0002576011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001903642,"about_ca_system_score_gemma":0.00006394523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002920775,"about_ca_topic_score_gemma":0.000001266395,"domain_scores_codex":[0.9979972,0.00006134751,0.0003166218,0.0004666106,0.0005121654,0.00064603],"domain_scores_gemma":[0.9980649,0.001244058,0.00003824877,0.0004167254,0.00005781782,0.000178257],"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":[0.000002352924,0.00002121031,0.4431038,0.00009710897,0.000006592563,0.0001005815,0.0001321373,0.5551315,0.0007100438,0.00002592199,0.00008390458,0.0005848475],"study_design_scores_gemma":[0.0002025871,0.00003059547,0.3664149,0.00005753236,8.431604e-7,0.000004478646,0.000001226104,0.6256896,0.0002029371,0.000002517226,0.007199021,0.0001937924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2658264,0.00008593258,0.7295107,0.0002417759,0.000560855,0.0001757034,0.000006239956,0.003590116,0.000002245211],"genre_scores_gemma":[0.9960705,0.00001132663,0.003240366,0.00004593772,0.0001179612,0.0001164853,0.0001125114,0.00006060239,0.0002242916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7302441,"threshold_uncertainty_score":0.9677247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02440577382411849,"score_gpt":0.2681081263815844,"score_spread":0.2437023525574659,"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."}}