{"id":"W2096370414","doi":"10.1109/ase.2009.89","title":"Evaluating the Accuracy of Fault Localization Techniques","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Process (computing); Assertion; Artificial intelligence; Fault (geology); Class (philosophy); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03183934,0.00156446,0.001745097,0.009959233,0.0007651304,0.002990886,0.002913278,0.003053902,0.0009770753],"category_scores_gemma":[0.2007105,0.0005180684,0.001745819,0.005275943,0.001470055,0.005304466,0.001726119,0.001710439,0.000942484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001452726,"about_ca_system_score_gemma":0.001159874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002989489,"about_ca_topic_score_gemma":0.002882283,"domain_scores_codex":[0.9425495,0.01842337,0.006431099,0.005679529,0.0250791,0.00183736],"domain_scores_gemma":[0.6666535,0.244723,0.02219452,0.03493897,0.03021831,0.001271653],"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":[0.001752817,0.000684806,0.2304805,0.001332909,0.001588565,0.0003157583,0.0008746974,0.1663956,0.01518718,0.006768191,0.00629535,0.5683236],"study_design_scores_gemma":[0.0001761274,0.002057071,0.06439114,0.0003096603,0.00063382,0.0007056966,0.0006103001,0.8524858,0.06167388,0.01120927,0.005588115,0.0001591314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6171386,0.00497782,0.358328,0.002244965,0.0002789664,0.0002678364,0.001631562,0.006567952,0.008564296],"genre_scores_gemma":[0.884936,0.0006028304,0.1116247,0.0002302048,0.00008712527,0.00009976509,0.001393049,0.0002919151,0.0007345298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03183934,"threshold_uncertainty_score":0.1683846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05549973097779415,"score_gpt":0.3941240675486642,"score_spread":0.33862433657087,"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."}}