{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005499949,0.00003951404,0.00004500618,0.00004635044,0.00003872067,0.00004360256,0.0005750855,0.0000198284,0.000009443599],"category_scores_gemma":[0.001703018,0.00002489851,0.00001729445,0.0003774264,0.00001314163,0.0001793204,0.00007159729,0.00005891854,0.000005576829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496323,"about_ca_system_score_gemma":0.00003288494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001188215,"about_ca_topic_score_gemma":2.940841e-7,"domain_scores_codex":[0.9993547,0.00003250903,0.0001056683,0.000102871,0.0003029692,0.0001012772],"domain_scores_gemma":[0.9988906,0.0005806063,0.00002815414,0.0003623383,0.0001214982,0.000016752],"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":[0.000001643912,0.00002494381,0.0006204216,0.000007895501,0.000003282491,7.389374e-7,0.0003560069,0.004821199,0.01002484,0.02837661,0.001167344,0.9545951],"study_design_scores_gemma":[0.00006643376,0.0002716274,0.007460858,0.00002475954,0.000001301687,0.000004529081,0.000008926171,0.8355088,0.1507949,0.00515421,0.0006232068,0.00008047747],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009503297,0.00003529455,0.9886593,0.000738876,0.00002465711,0.0001194431,6.625398e-8,0.0002956015,0.0006234711],"genre_scores_gemma":[0.8848811,0.00000493455,0.1148365,0.0001688938,0.00001742154,0.000004862621,2.601061e-7,0.000002053482,0.00008390265],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9545146,"threshold_uncertainty_score":0.2038795,"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."}}