{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006046459,0.0005377589,0.0006633843,0.0003138114,0.0001510323,0.0003988017,0.0004354717,0.0003152572,1.351751e-7],"category_scores_gemma":[0.04216209,0.00059479,0.00008629919,0.0007862246,0.00002855277,0.0005749527,0.0009636826,0.0008243492,0.000001065196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004317493,"about_ca_system_score_gemma":0.0001239981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000405175,"about_ca_topic_score_gemma":0.000006850968,"domain_scores_codex":[0.9970766,0.0001051949,0.0008042954,0.001277625,0.0002269922,0.0005093357],"domain_scores_gemma":[0.9894244,0.009154974,0.0002890794,0.0006842159,0.0002634804,0.0001838599],"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":[0.000003451529,0.00003192735,0.05129757,0.004225197,0.00002991999,0.004345784,0.000879021,0.9202151,0.0006256874,0.0001270643,0.00003216991,0.01818713],"study_design_scores_gemma":[0.0002247239,0.00005275925,0.01515718,0.0008691901,0.00002602768,0.004743444,0.00003606853,0.9779527,0.0001531111,0.0001197512,0.00004029468,0.0006247436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1051946,0.0003119831,0.8882762,0.0001574445,0.0007024568,0.001077879,0.00004001715,0.004238902,5.180662e-7],"genre_scores_gemma":[0.3570429,0.000004252738,0.6423373,0.00001444445,0.0002523721,0.000262137,0.0000182911,0.00006585076,0.000002422149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2518484,"threshold_uncertainty_score":0.9996504,"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."}}