{"id":"W4401905742","doi":"10.1109/icst60714.2024.00055","title":"Insights into System Failures: ML-Assisted Testing and Failure Models for Cyber-Physical Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cyber-physical system; Computer science; Reliability engineering; System testing; Engineering; Software engineering; Operating system","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002318244,0.0002396597,0.0002970899,0.0001977441,0.0002398169,0.001052237,0.0004927298,0.0001044274,9.346442e-8],"category_scores_gemma":[0.0002320748,0.0001812786,0.00007059734,0.0005712258,0.00004521685,0.0006436309,0.0002487861,0.0001514461,0.000007808254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009596126,"about_ca_system_score_gemma":0.00009606444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006082641,"about_ca_topic_score_gemma":0.00001438744,"domain_scores_codex":[0.9984313,0.00005971162,0.000280182,0.00069112,0.0002573966,0.0002802588],"domain_scores_gemma":[0.9972541,0.001873686,0.00005667045,0.0005023207,0.0001838976,0.0001293239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000351778,0.00004739636,0.0000641021,0.002083043,0.00006311115,0.00007024955,0.002287111,0.0007632181,0.001209955,0.9405091,0.01933873,0.03356042],"study_design_scores_gemma":[0.00009070183,0.0001110905,0.00001640374,0.0009143918,0.0000164968,0.0001047986,0.00005451299,0.9290581,0.0001708403,0.0683319,0.0008885218,0.0002422155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005754381,0.0007646348,0.9625916,0.0003155182,0.0003100596,0.0004578761,0.000001835201,0.02876495,0.001039079],"genre_scores_gemma":[0.6846511,6.022292e-7,0.3149204,0.00002576221,0.0001391952,0.0001515139,0.000001395782,0.00002067807,0.00008938481],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9282949,"threshold_uncertainty_score":0.9999847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03310137089038518,"score_gpt":0.2653385997456784,"score_spread":0.2322372288552932,"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."}}