{"id":"W4400680834","doi":"10.1109/saner60148.2024.00038","title":"Predicting Line-Level Defects by Capturing Code Contexts with Hierarchical Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Advancements in Photolithography Techniques","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Transformer; Engineering; Voltage; Electrical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00009204086,0.0002225042,0.0001655299,0.0001311543,0.00005053929,0.0000574339,0.000117895,0.00008021198,0.00004605959],"category_scores_gemma":[0.000005761168,0.0001796249,0.0000650405,0.0002390577,0.0000675409,0.0002365814,0.00001300767,0.0003684359,0.000004899905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005918204,"about_ca_system_score_gemma":0.00001377774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001778457,"about_ca_topic_score_gemma":0.00006144406,"domain_scores_codex":[0.9989585,0.00001015096,0.0002106653,0.0002538815,0.0002035746,0.0003632026],"domain_scores_gemma":[0.999663,0.0000784719,0.000008469318,0.000131093,0.00001556948,0.0001034051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003770638,0.0003652571,0.02812145,0.006422134,0.003513957,0.0008520733,0.008903844,0.02248717,0.4050607,0.03340466,0.02884428,0.4616474],"study_design_scores_gemma":[0.001308284,0.0005788285,0.0006346519,0.001518709,0.0001845181,0.0001702379,0.0003781823,0.2066973,0.722697,0.002681275,0.06145808,0.001692913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1771619,0.001382093,0.7916069,0.00004058062,0.0002136688,0.0004076872,0.000132359,0.004358956,0.02469578],"genre_scores_gemma":[0.984078,0.0001326751,0.01523942,0.00005138526,0.00004680242,0.00009277521,0.00001701869,0.00008236936,0.0002595792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.806916,"threshold_uncertainty_score":0.7324891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01069823642654041,"score_gpt":0.2428276949111506,"score_spread":0.2321294584846101,"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."}}