{"id":"W3081900038","doi":"","title":"Unit Test Effort Prioritization Using Combined Datasets and Deep Learning: A Cross-Systems Validation.","year":2020,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Prioritization; Computer science; Test (biology); Artificial intelligence; Unit (ring theory); Unit testing; Cross-validation; Machine learning; Data mining; Engineering; Software; Mathematics","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":[0.0002911385,0.0003189926,0.0002992546,0.0001867514,0.0001870544,0.0004806508,0.0003092851,0.0001275349,9.867213e-7],"category_scores_gemma":[0.002516396,0.000359098,0.00003434238,0.0005898795,0.00002584859,0.0004922376,0.0003345319,0.0003407148,0.000004382228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003988537,"about_ca_system_score_gemma":0.00003939396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001378465,"about_ca_topic_score_gemma":2.209631e-7,"domain_scores_codex":[0.9986185,0.00001938016,0.0003273129,0.0005043414,0.0001658635,0.0003645449],"domain_scores_gemma":[0.9986643,0.0006009823,0.0000719306,0.0002751167,0.0001071516,0.0002805411],"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":[0.00001311262,0.0001149391,0.3451356,0.002861524,0.0001313892,0.00009325374,0.003668159,0.6250912,0.002965442,0.004174596,0.0004653782,0.01528537],"study_design_scores_gemma":[0.0003337083,0.0001103733,0.005364256,0.0002103638,0.00001590699,0.00006531958,0.000004308893,0.9905829,0.0004187674,0.00002885345,0.002443745,0.0004214507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06205415,0.002196108,0.925528,0.00002179621,0.0003019766,0.0001934688,0.00001124892,0.009686483,0.000006698947],"genre_scores_gemma":[0.8192527,0.0000474566,0.1803541,0.00001313356,0.0001813823,0.00002255799,0.00005148246,0.00006208108,0.00001506612],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7571986,"threshold_uncertainty_score":0.9998861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02080212164416674,"score_gpt":0.2542011728348439,"score_spread":0.2333990511906772,"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."}}