{"id":"W4391211964","doi":"10.48550/arxiv.2401.12364","title":"Guiding the Search Towards Failure-Inducing Test Inputs Using Support Vector Machines","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Support vector machine; Sorting; Computer science; Machine learning; Artificial intelligence; Structured support vector machine; Genetic algorithm; Data mining; Pattern recognition (psychology); Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001023473,0.0004461655,0.0003686855,0.0004497664,0.0004241765,0.0006349696,0.002981254,0.0003042589,0.00001810767],"category_scores_gemma":[0.0004239916,0.000388118,0.0002633716,0.001181239,0.0001441724,0.0002437321,0.007359141,0.001089151,0.00006872444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004120403,"about_ca_system_score_gemma":0.0007604627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001330884,"about_ca_topic_score_gemma":0.00003282454,"domain_scores_codex":[0.9973751,0.0001775169,0.0002811966,0.001371016,0.0002330849,0.0005620526],"domain_scores_gemma":[0.9971131,0.0005594051,0.0001715126,0.001759775,0.000236362,0.0001598627],"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":[0.00008481343,0.001046326,0.112274,0.0043389,0.001850811,0.01847007,0.01980099,0.4030955,0.006375053,0.2558472,0.1096398,0.06717659],"study_design_scores_gemma":[0.0001071432,0.00006691543,0.000590756,0.0005801583,0.0001020687,0.00009766413,0.00001757165,0.9105651,0.001175838,0.08572709,0.0003456063,0.0006240814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.280432,0.0001595627,0.7007833,0.001542738,0.001722649,0.000524313,0.0000311681,0.01302908,0.00177519],"genre_scores_gemma":[0.9729615,0.00002255832,0.02598437,0.0001848408,0.0002545605,0.00000154113,0.00000681828,0.00004622794,0.0005376208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6925294,"threshold_uncertainty_score":0.9998571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1550150396804565,"score_gpt":0.2468635168500394,"score_spread":0.09184847716958283,"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."}}