{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001252988,0.001110598,0.0006877715,0.0006989874,0.000261361,0.0007055269,0.001860276,0.0009026346,0.003563185],"category_scores_gemma":[0.006046169,0.0004829761,0.0008584764,0.0005293546,0.000954313,0.001515466,0.001326653,0.00185049,0.0004962036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007033112,"about_ca_system_score_gemma":0.000703852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001296274,"about_ca_topic_score_gemma":0.001666291,"domain_scores_codex":[0.9990311,0.0003807934,0.00004319626,0.0001295955,0.0003321957,0.00008323065],"domain_scores_gemma":[0.9969018,0.002205758,0.0001656134,0.0004054073,0.0002481336,0.00007325776],"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":[0.0001570185,0.0001736282,0.0008052049,0.0001647096,0.00006869738,0.0001216827,0.00007831426,0.6971131,0.005045162,0.05696083,0.00200629,0.2373054],"study_design_scores_gemma":[0.00001012214,0.00002812926,0.00007588744,0.00001217503,0.000008803446,0.00003637919,0.000004157922,0.9589361,0.001603943,0.03870169,0.0005775215,0.000005125386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009562295,0.0002166581,0.9849597,0.0001124061,0.00002736897,0.00003741473,0.00002099117,0.001098914,0.003964242],"genre_scores_gemma":[0.5392058,0.0002968481,0.4553741,0.00009236029,0.00004344377,0.00013379,0.0001288115,0.0003235759,0.004401328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003563185,"threshold_uncertainty_score":0.01192009,"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."}}