{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002832643,0.001931206,0.0008395571,0.003412732,0.0006174646,0.001837373,0.0037042,0.001624166,0.004682538],"category_scores_gemma":[0.01944613,0.001003499,0.001188179,0.001065791,0.001459358,0.003935099,0.003895598,0.002194976,0.001626251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001099871,"about_ca_system_score_gemma":0.002098576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003540368,"about_ca_topic_score_gemma":0.004680603,"domain_scores_codex":[0.9969024,0.0007878632,0.000218938,0.0007106295,0.001113862,0.0002662971],"domain_scores_gemma":[0.9916427,0.004277201,0.0008151605,0.002000335,0.0009910002,0.000273545],"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":[0.001153811,0.0004360296,0.03028672,0.0008987847,0.0003087413,0.001123868,0.001093362,0.1392265,0.03746735,0.04749131,0.02595943,0.7145542],"study_design_scores_gemma":[0.0001271934,0.0002747231,0.001654133,0.0001125202,0.00007388101,0.0004009415,0.0001196044,0.912624,0.02617426,0.04515174,0.01320758,0.00007938289],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01891107,0.0005349147,0.9062811,0.0002418095,0.0001414096,0.0001711798,0.0006555911,0.07131638,0.001746497],"genre_scores_gemma":[0.5022671,0.0004677356,0.4835356,0.0005786091,0.0001267581,0.0004658859,0.003027644,0.005031899,0.004498747],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004682538,"threshold_uncertainty_score":0.01566464,"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."}}