{"id":"W2888962833","doi":"","title":"Poster: Designing Bug Detection Rules for Fewer False Alarms","year":2018,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"False positive paradox; Computer science; Software bug; Constant false alarm rate; Open source; Static analysis; False alarm; True positive rate; False positives and false negatives; False positive rate; Data mining; Machine learning; Artificial intelligence; Software; Programming language","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":[0.0003406444,0.0002392662,0.0001667596,0.0004044133,0.0001116504,0.0003717865,0.001112752,0.0001050216,0.00004888019],"category_scores_gemma":[0.002102995,0.0002512285,0.0000923064,0.0002130451,0.0000350834,0.0005255635,0.0002004828,0.0002377945,0.0001666789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001851532,"about_ca_system_score_gemma":0.00006499566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001152104,"about_ca_topic_score_gemma":0.000003360174,"domain_scores_codex":[0.9982745,0.0000168371,0.0002583406,0.0005044149,0.0005237947,0.0004221203],"domain_scores_gemma":[0.9981326,0.0006305018,0.00006111568,0.0004017689,0.0006420518,0.0001319715],"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":[0.000652928,0.0006765407,0.03730047,0.0005427572,0.001460131,0.000221625,0.006063818,0.02456752,0.2411173,0.2536577,0.003669776,0.4300694],"study_design_scores_gemma":[0.002001331,0.001283408,0.03218535,0.0006770436,0.00001949544,0.0001298454,0.00004756972,0.680185,0.261648,0.00345649,0.01665358,0.001712924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05749389,0.0000223523,0.938795,0.0001904803,0.002183075,0.0002353606,0.00001592179,0.0009516423,0.0001122476],"genre_scores_gemma":[0.8875837,0.000005590719,0.1115068,0.00008075211,0.0004747123,0.0001240879,0.00001181273,0.00003744261,0.0001751852],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8300897,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03837499704633768,"score_gpt":0.2935458189583928,"score_spread":0.2551708219120551,"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."}}