{"id":"W3159729842","doi":"10.1109/icas49788.2021.9551151","title":"Quality Assurance Challenges For Machine Learning Software Applications During Software Development Life Cycle Phases","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Systems development life cycle; Quality assurance; Software quality assurance; Computer science; Software quality analyst; Software engineering; Software quality; Software quality control; Software; Software development process; Quality (philosophy); Software development; Engineering management; Process management; Data science; Engineering; Operations management","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":[0.001099372,0.0006572943,0.000879431,0.0002080418,0.001032999,0.0005079075,0.002231283,0.0004030638,0.00007247719],"category_scores_gemma":[0.00313124,0.000706182,0.0003159051,0.0002832061,0.0000625497,0.0004628143,0.004090153,0.001428259,0.00001599665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002692134,"about_ca_system_score_gemma":0.001001446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001025471,"about_ca_topic_score_gemma":0.0002151644,"domain_scores_codex":[0.9952941,0.0003639118,0.0009868374,0.001937801,0.0007140787,0.0007032975],"domain_scores_gemma":[0.9954507,0.001512502,0.0007674449,0.001487962,0.0005011803,0.0002801798],"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":[0.00003581732,0.0003628136,0.008114886,0.003652204,0.0004246623,0.00001795496,0.003552117,0.7328359,0.00006505495,0.002962171,0.00004231563,0.2479341],"study_design_scores_gemma":[0.01279323,0.0003115948,0.1957573,0.004969313,0.0004117253,0.0001465536,0.003713959,0.6131548,0.008567272,0.01981198,0.1227328,0.01762946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005665459,0.00521173,0.9843541,0.0009004197,0.0005609788,0.001116885,0.00001531485,0.001938916,0.000236227],"genre_scores_gemma":[0.1739431,0.0003983173,0.8227821,0.0001259413,0.0003378957,0.001493117,0.0002228633,0.00007713938,0.0006195204],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2303046,"threshold_uncertainty_score":0.999539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0452561642815391,"score_gpt":0.3155992123112202,"score_spread":0.2703430480296811,"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."}}