{"id":"W2946929989","doi":"10.1007/s10664-020-09853-4","title":"Automating system test case classification and prioritization for use case-driven testing in product lines","year":2020,"lang":"en","type":"preprint","venue":"Empirical Software Engineering","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"H2020 European Research Council; Fonds National de la Recherche Luxembourg","keywords":"Computer science; Requirement prioritization; Test strategy; Context (archaeology); Domain engineering; Test case; Software product line; New product development; Risk-based testing; Software engineering; Software development; Systems engineering; Reliability engineering; Software; Engineering; Machine learning; Requirement; Component-based software engineering; Software construction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004927715,0.001336021,0.001265226,0.005162145,0.0006778929,0.002556637,0.001882707,0.001074405,0.003108484],"category_scores_gemma":[0.02709447,0.0007000763,0.0008121968,0.001748815,0.0004805773,0.001340349,0.001565497,0.001266049,0.001273377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009612066,"about_ca_system_score_gemma":0.002937043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009783866,"about_ca_topic_score_gemma":0.01662215,"domain_scores_codex":[0.9936004,0.002350032,0.0005787243,0.0008774572,0.002045642,0.0005477193],"domain_scores_gemma":[0.966861,0.02145087,0.002856934,0.002709409,0.005194934,0.0009268684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006098682,0.00108302,0.05314092,0.000442732,0.0001310854,0.0003287957,0.0007567275,0.03266013,0.05312477,0.002071091,0.006213799,0.8494371],"study_design_scores_gemma":[0.0001386796,0.0003507414,0.03395892,0.0001147072,0.0001167731,0.0005162592,0.0004635013,0.9012247,0.05299494,0.006314626,0.003741586,0.0000645781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3125459,0.0004808046,0.6693227,0.0004009847,0.00005836917,0.0009650152,0.0008863943,0.01257296,0.00276681],"genre_scores_gemma":[0.5646073,0.0001178908,0.431242,0.0001002541,0.00002215597,0.0002976746,0.001758215,0.0004033874,0.001451222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009783866,"threshold_uncertainty_score":0.02606052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1806578268655053,"score_gpt":0.3437937593456182,"score_spread":0.1631359324801129,"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."}}