{"id":"W4391579662","doi":"10.1145/3597503.3623321","title":"FuzzSlice: Pruning False Positives in Static Analysis Warnings through Function-Level Fuzzing","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuzz testing; False positive paradox; Static analysis; Computer science; Function (biology); Pruning; Crash; Code (set theory); False positives and false negatives; Data mining; Machine learning; Software; Programming language; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001016449,0.0004436481,0.0006301558,0.001671903,0.00009413744,0.0009665401,0.001513544,0.0002680443,0.0000593369],"category_scores_gemma":[0.0006518027,0.0004314609,0.000307337,0.003782887,0.00005012798,0.0004220802,0.004591813,0.001978536,0.0001739364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004085558,"about_ca_system_score_gemma":0.0003562775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001364585,"about_ca_topic_score_gemma":0.0001530608,"domain_scores_codex":[0.9962602,0.0001590045,0.0005771932,0.001421142,0.0008949797,0.0006874751],"domain_scores_gemma":[0.9969329,0.001436668,0.0001181963,0.001196904,0.0001866183,0.0001287775],"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":[0.00004433685,0.0003546874,0.07515811,0.003502412,0.008311425,0.001022485,0.08162717,0.718508,0.0008275949,0.06004234,0.00344772,0.04715372],"study_design_scores_gemma":[0.0002965504,0.00008582014,0.1352884,0.0008664462,0.0004180024,0.00001123106,0.0005183865,0.8213471,0.0003429682,0.03919723,0.0004150119,0.001212824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1096984,0.0009855976,0.885343,0.000831036,0.0007517036,0.0003447312,0.00001641674,0.001047075,0.0009821373],"genre_scores_gemma":[0.8906449,0.00004865548,0.1069996,0.0001207552,0.00008754624,0.0001322041,0.00003276505,0.00004731282,0.001886274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7809466,"threshold_uncertainty_score":0.9998137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04030937211425523,"score_gpt":0.3156704504588826,"score_spread":0.2753610783446274,"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."}}