{"id":"W4390189471","doi":"10.1109/milcom58377.2023.10356308","title":"Input Output Grammar Coverage in Fuzzing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"","keywords":"Fuzz testing; Computer science; Grammar; Code coverage; Code (set theory); Natural language processing; Data mining; Artificial intelligence; Programming language; Set (abstract data type); Software","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":[],"consensus_categories":[],"category_scores_codex":[0.000441352,0.00008164922,0.00009814628,0.0002486864,0.0000484932,0.000108177,0.0005221817,0.00004200623,0.000003182048],"category_scores_gemma":[0.0002836953,0.0000746621,0.00002889628,0.0009714368,0.00001305697,0.00019969,0.0003197279,0.0001041033,0.0002106914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002837101,"about_ca_system_score_gemma":0.00002980432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000204719,"about_ca_topic_score_gemma":0.00001407737,"domain_scores_codex":[0.9991477,0.00003122295,0.0001427215,0.0002573101,0.0001591598,0.0002618809],"domain_scores_gemma":[0.9992419,0.0002678233,0.00002524054,0.0003997414,0.00002148442,0.0000437388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002991767,0.00006452727,0.1028778,0.00003106169,0.000007051957,0.0003808786,0.001303105,0.0003630875,0.0001320911,0.04771754,0.2188927,0.6282272],"study_design_scores_gemma":[0.0004806702,0.0001175664,0.08264044,0.0001279051,0.00000191336,0.00003712112,0.00001081258,0.2620532,0.001199514,0.6394281,0.01330129,0.000601438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04345979,0.00002555359,0.8934067,0.001379436,0.0003073958,0.0001250542,4.993617e-7,0.04848526,0.01281032],"genre_scores_gemma":[0.907218,0.000009849399,0.09100101,0.0006324547,0.00002735139,0.00001518516,0.000001616653,0.000008207704,0.001086278],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8637583,"threshold_uncertainty_score":0.3044632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0327188498718898,"score_gpt":0.2711694917751658,"score_spread":0.238450641903276,"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."}}