{"id":"W2756297985","doi":"10.1007/978-3-319-67549-7_1","title":"Fragility-Oriented Testing with Model Execution and Reinforcement Learning","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Fragility; Reinforcement learning; Computer science; Reinforcement; Stress testing (software); Artificial intelligence; Engineering; Operating system; Structural engineering","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":[0.0009920612,0.000441553,0.0003913604,0.0004648941,0.0007779769,0.0006506724,0.001574086,0.0002093338,0.000001036653],"category_scores_gemma":[0.0006910508,0.0003755168,0.00003972461,0.00020161,0.0007136731,0.0006208598,0.001323031,0.0008881683,0.000002861939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001895819,"about_ca_system_score_gemma":0.0004156591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007290976,"about_ca_topic_score_gemma":0.00001203593,"domain_scores_codex":[0.9970455,0.00002160156,0.0003389196,0.001309072,0.0007671479,0.0005177149],"domain_scores_gemma":[0.9972585,0.0005280097,0.000414188,0.001295885,0.0003571525,0.0001462207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007951231,0.0000116835,0.001239182,0.00005468752,0.000007691666,0.00005834943,0.0007798175,0.3378693,0.00003597067,0.006062065,0.00001828109,0.653855],"study_design_scores_gemma":[0.0001394432,0.0002521157,0.0001234307,0.0007870019,0.000006047778,0.00008201097,2.976951e-8,0.8520257,0.0001507334,0.1459292,0.00009994812,0.0004043642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001452638,0.0001153757,0.9934084,0.0001714675,0.0001962024,0.0002751556,5.357996e-7,0.002296492,0.003391077],"genre_scores_gemma":[0.3371258,0.000009243464,0.6622537,0.0002257579,0.00007759874,0.000008737505,0.0000022226,0.0000204169,0.0002765001],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6534507,"threshold_uncertainty_score":0.9998697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02738793666073401,"score_gpt":0.2561419108886857,"score_spread":0.2287539742279517,"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."}}