{"id":"W2978699951","doi":"10.48550/arxiv.1910.02452","title":"Can we rely on smartphone applications?","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Android (operating system); Computer science; Weibull distribution; Reliability (semiconductor); Mobile device; Smartphone application; Software; Software quality; Reliability engineering; World Wide Web; Multimedia; Engineering; Operating system; Software development","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003461597,0.0002624179,0.0003528088,0.0003958904,0.000166257,0.0001622537,0.002662528,0.0002882125,0.00004458521],"category_scores_gemma":[0.00004927323,0.0002862456,0.0003011654,0.001108895,0.0001106172,0.0001414926,0.001929329,0.000838041,0.001024566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003444745,"about_ca_system_score_gemma":0.0003754509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003356018,"about_ca_topic_score_gemma":0.00004897443,"domain_scores_codex":[0.9976203,0.0001881132,0.0001896078,0.001422298,0.0002033998,0.0003763034],"domain_scores_gemma":[0.9965052,0.0003239775,0.0001584682,0.00259964,0.0002122618,0.0002004585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006379173,0.0006390776,0.01009263,0.00044091,0.0003613821,0.0001816256,0.0003367054,0.5535435,0.00003913369,0.4095373,0.003067127,0.02169687],"study_design_scores_gemma":[0.0008421499,0.0001786345,0.003364366,0.0002517079,0.0001022232,0.000003994025,0.00007147426,0.6779783,0.0003913409,0.2862771,0.02934854,0.00119017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05066137,0.0001369071,0.9414335,0.002620669,0.0002657639,0.0007019909,0.00002901762,0.0004254748,0.003725262],"genre_scores_gemma":[0.9925088,0.0006997246,0.000862192,0.0001890946,0.00007019988,0.000005493193,0.00002266589,0.00001440614,0.00562739],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9418474,"threshold_uncertainty_score":0.999959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07682296760132028,"score_gpt":0.2115360905432773,"score_spread":0.134713122941957,"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."}}