{"id":"W4407098050","doi":"10.1109/tse.2025.3535938","title":"One Sentence Can Kill the Bug: Auto-Replay Mobile App Crashes From One-Sentence Overviews","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Computer science; Sentence; Natural language processing; Artificial intelligence; Speech recognition","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":[0.001491926,0.002479533,0.0007215249,0.001678048,0.0003475401,0.0007065416,0.001825389,0.001077528,0.00214094],"category_scores_gemma":[0.01430951,0.0006873014,0.0008956536,0.0004688239,0.0005262513,0.001533156,0.001776646,0.001173608,0.001382061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003438499,"about_ca_system_score_gemma":0.0008508968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005812261,"about_ca_topic_score_gemma":0.00856003,"domain_scores_codex":[0.9985322,0.0004070218,0.0001131064,0.0004077263,0.0004609123,0.00007906024],"domain_scores_gemma":[0.992862,0.004226751,0.000673219,0.001091019,0.000935381,0.0002115939],"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":[0.003801031,0.0007754678,0.05361499,0.003443373,0.0006780685,0.008921466,0.006443066,0.07456873,0.08686287,0.002464058,0.08698018,0.6714467],"study_design_scores_gemma":[0.0003589569,0.001450474,0.02858065,0.0002548837,0.0004742648,0.003066984,0.00132368,0.8382226,0.08421553,0.005286996,0.03646008,0.0003049657],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4297048,0.002854654,0.2357012,0.0007958767,0.0004462062,0.0006032423,0.01035047,0.3162776,0.003265874],"genre_scores_gemma":[0.7819307,0.0007245181,0.1854683,0.0004402701,0.000117508,0.0003592619,0.02175071,0.005497194,0.003711536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005812261,"threshold_uncertainty_score":0.01155686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.012259137582423,"score_gpt":0.2343189056311032,"score_spread":0.2220597680486802,"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."}}