{"id":"W4402460553","doi":"10.1007/s10664-024-10536-7","title":"Quality issues in machine learning software systems","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software quality; Quality (philosophy); Software engineering; Software; Software development; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008984094,0.0002679532,0.0003380534,0.0003060975,0.00009016041,0.0005444787,0.0006957834,0.0001397366,0.00002766192],"category_scores_gemma":[0.001947575,0.0002604991,0.0001067841,0.001279749,0.00002226869,0.0007546394,0.0003044161,0.0006934678,0.0003176087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002491481,"about_ca_system_score_gemma":0.00006160173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005549881,"about_ca_topic_score_gemma":0.00002777346,"domain_scores_codex":[0.9976718,0.0001210304,0.0005364362,0.0006381862,0.0004308698,0.00060161],"domain_scores_gemma":[0.9982638,0.001049557,0.0000370722,0.0004277691,0.00005751731,0.0001643354],"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":[0.000008913978,0.0001171837,0.1842117,0.001053232,0.00006685538,0.0009463278,0.005036966,0.7523727,0.0004723591,0.01943529,0.001682807,0.03459569],"study_design_scores_gemma":[0.00008031623,0.00007946778,0.008508105,0.0004067263,0.000004291565,0.0000380241,0.00006830937,0.864954,0.0009978769,0.0007993553,0.1234009,0.0006626181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03952623,0.008408898,0.9471647,0.0005884491,0.001209002,0.000170512,0.000003357401,0.002885562,0.00004334557],"genre_scores_gemma":[0.9464851,0.00008146973,0.0519371,0.000103697,0.0003080824,0.00006983627,0.000009740812,0.00006422296,0.0009407747],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9069589,"threshold_uncertainty_score":0.9999847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04127975929546383,"score_gpt":0.3288721992370755,"score_spread":0.2875924399416117,"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."}}