{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001941003,0.001438125,0.001048321,0.001203355,0.0003794434,0.0008332402,0.001718524,0.001328364,0.001377647],"category_scores_gemma":[0.01110929,0.0004703238,0.000744385,0.0004401699,0.0009996855,0.001032865,0.001046896,0.001437807,0.0003696818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007172508,"about_ca_system_score_gemma":0.00148065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002848711,"about_ca_topic_score_gemma":0.002843549,"domain_scores_codex":[0.9983085,0.0007592054,0.00007846101,0.0002759877,0.0004232544,0.0001545243],"domain_scores_gemma":[0.9933211,0.005110684,0.0004825381,0.0002979797,0.000616324,0.0001713005],"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":[0.0001293802,0.0001760455,0.004771312,0.0001109796,0.00006341756,0.0002040015,0.0001098651,0.8613815,0.00461538,0.004616532,0.001050423,0.1227711],"study_design_scores_gemma":[0.00001470605,0.00008653357,0.0001733251,0.00001269868,0.000009141182,0.00003352912,0.00001827453,0.9953678,0.001432553,0.002594745,0.000251747,0.000005081447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1256893,0.0005030958,0.8695516,0.0005071188,0.00004722523,0.0001065477,0.00007041345,0.001652523,0.001872191],"genre_scores_gemma":[0.8236136,0.0001113412,0.1745324,0.0002460052,0.00002251659,0.0001388259,0.000179232,0.0001316549,0.001024442],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002848711,"threshold_uncertainty_score":0.01026517,"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."}}