{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02211966,0.0003836676,0.0008665881,0.00294789,0.001267877,0.004714589,0.001751217,0.002388411,0.003987385],"category_scores_gemma":[0.179483,0.0008601483,0.0006793672,0.003067149,0.007053782,0.0127577,0.001929564,0.002890493,0.0002237528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003705777,"about_ca_system_score_gemma":0.002020714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00367775,"about_ca_topic_score_gemma":0.001876968,"domain_scores_codex":[0.9849813,0.007208245,0.001004878,0.001019235,0.005212692,0.0005737111],"domain_scores_gemma":[0.7420443,0.2244218,0.01062421,0.01081224,0.01083905,0.001258455],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00005107715,0.00010983,0.00835857,0.000312152,0.00005529039,0.00007753504,0.0009446517,0.02234489,0.0002387976,0.922821,0.001653181,0.04303309],"study_design_scores_gemma":[0.0000163939,0.00003021434,0.002496393,0.00007917203,0.00001538491,0.00004465812,0.0002083434,0.03263488,0.0002743576,0.9620258,0.002162308,0.00001215604],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2432344,0.02784397,0.6456067,0.04937709,0.0004587859,0.0001778051,0.0002482863,0.0003877394,0.03266531],"genre_scores_gemma":[0.9649547,0.002187594,0.02977113,0.0004194393,0.0004279023,0.00006565361,0.00009093014,0.00009654995,0.001985966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778804,"threshold_uncertainty_score":0.1169813,"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."}}