{"id":"W7125982494","doi":"10.1109/ase63991.2025.00211","title":"DRIFT: Debug-based Trace Inference for Firmware Testing","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Firmware; Fuzz testing; Debugging; Concept drift; Binary number; Source code; TRACE (psycholinguistics); Interrupt","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001075062,0.0005463799,0.0005400449,0.0004392619,0.0007995266,0.0008563694,0.002043364,0.0003208069,0.0000326058],"category_scores_gemma":[0.01412497,0.0005448739,0.000232782,0.002220358,0.0001862491,0.0004067687,0.0004791052,0.0004074005,0.00001764967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001568236,"about_ca_system_score_gemma":0.00177069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003966436,"about_ca_topic_score_gemma":0.00003568022,"domain_scores_codex":[0.996442,0.0001145593,0.000813133,0.00129104,0.0003698859,0.0009694],"domain_scores_gemma":[0.9863027,0.010712,0.0002758786,0.001522969,0.000982389,0.0002040481],"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":[0.00003156302,0.0003463157,0.0473189,0.0005623351,0.00004058464,0.00001513674,0.0002306615,0.0009123965,0.00008572156,0.01688232,0.06965014,0.8639239],"study_design_scores_gemma":[0.0006966704,0.0004397332,0.00375316,0.001657614,0.0000540392,0.000004819954,0.000007230572,0.9152402,0.003666932,0.069016,0.004822584,0.0006410724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006638092,0.0006853191,0.9669805,0.003547405,0.0007137964,0.0009446919,0.00001415744,0.01915496,0.007295398],"genre_scores_gemma":[0.49442,0.000002479086,0.5021948,0.001652002,0.00005490273,0.0001521235,0.000002586395,0.00001752739,0.001503615],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9143277,"threshold_uncertainty_score":0.9997002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05398414036472179,"score_gpt":0.3325451358902314,"score_spread":0.2785609955255096,"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."}}