{"id":"W4385977849","doi":"10.1007/s41870-023-01390-9","title":"A study of the interactive role of metamorphic testing and machine learning in the quality assurance of a deep learning forecasting application","year":2023,"lang":"en","type":"article","venue":"International Journal of Information Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Mitacs","keywords":"Machine learning; Computer science; Artificial intelligence; Metamorphic rock; Generalization; Software quality; Deep learning; Quality (philosophy); Software; Algorithm; Software development; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001829458,0.00006138548,0.0001670343,0.0006503638,0.00004580749,0.00002233295,0.0008755419,0.00004183461,2.739014e-7],"category_scores_gemma":[0.007313619,0.00004103659,0.00003436711,0.0009922053,0.00005755015,0.0004817864,0.000254499,0.000374507,2.400593e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000251448,"about_ca_system_score_gemma":0.00003216519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000141812,"about_ca_topic_score_gemma":0.00001904874,"domain_scores_codex":[0.9985734,0.0001410831,0.0007735856,0.00005878475,0.0003830481,0.0000700507],"domain_scores_gemma":[0.9959552,0.001299682,0.001885483,0.0001333876,0.0007190658,0.00000714405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002727688,0.00008708541,0.5526252,0.00002734136,0.000057314,0.000002011953,0.0120959,0.009268311,0.001476945,0.002404092,0.000004591791,0.4219239],"study_design_scores_gemma":[0.001034736,0.000749379,0.3062636,0.0003983648,0.00001891793,0.000394581,0.008019372,0.6270078,0.007912796,0.04800891,0.00006690239,0.0001245933],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8899102,0.00004140138,0.1092181,0.0004055758,0.00004879339,0.0001370282,8.300097e-7,0.00015996,0.00007804883],"genre_scores_gemma":[0.9861764,0.000006187185,0.01378312,0.00001452843,0.000006501349,0.000009867227,5.768513e-7,0.000002150145,6.14765e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6177395,"threshold_uncertainty_score":0.8755614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03081026342351223,"score_gpt":0.3040353657264644,"score_spread":0.2732251023029522,"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."}}