{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018201,0.0003280521,0.000320091,0.00026791,0.0003284824,0.0001489735,0.001062308,0.0001309317,0.00003151418],"category_scores_gemma":[0.00006178235,0.0003211383,0.0001831479,0.001003447,0.00006331848,0.0004896158,0.00002188965,0.0006320066,0.00003091918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002473489,"about_ca_system_score_gemma":0.00007918656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004213766,"about_ca_topic_score_gemma":0.0001381367,"domain_scores_codex":[0.9980192,0.00005007817,0.0004205926,0.0006912439,0.0003921754,0.0004266929],"domain_scores_gemma":[0.9979245,0.0005211327,0.00009367384,0.001226468,0.0001268743,0.0001073646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000374396,0.0005353627,0.0001490248,0.0001929104,0.0003477143,0.00002629949,0.001391368,0.6268812,0.04000215,0.0008394914,0.0004859799,0.3291111],"study_design_scores_gemma":[0.0008217151,0.000274987,0.003674914,0.001187771,0.0001339222,0.00002859578,0.0001493558,0.1793626,0.7884535,0.001916627,0.02253293,0.001463058],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005324402,0.0002495067,0.9888349,0.000259546,0.001429728,0.0005362286,0.00005177247,0.003286057,0.00002783196],"genre_scores_gemma":[0.7601523,0.0002419211,0.2377488,0.0005638394,0.00006212338,0.0006759172,0.000002841193,0.00004374422,0.0005085465],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7548279,"threshold_uncertainty_score":0.9999241,"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."}}