{"id":"W4417132535","doi":"10.1109/saner-c66551.2025.00018","title":"Usability of Static Application Security Testing Workflows","year":2025,"lang":"","type":"article","venue":"","topic":"Web Application Security Vulnerabilities","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Usability; Workflow; Usability inspection; Key (lock); Cognitive walkthrough; Web usability; Vulnerability (computing); Pluralistic walkthrough","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002488043,0.000392639,0.0006658676,0.0002825977,0.0003018146,0.0002359447,0.001960404,0.0002256977,0.0001849307],"category_scores_gemma":[0.001552799,0.000425173,0.0001710982,0.003918902,0.0007115722,0.000640351,0.0009898971,0.0004619618,0.00008272292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002653058,"about_ca_system_score_gemma":0.0008946625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008625627,"about_ca_topic_score_gemma":0.000120689,"domain_scores_codex":[0.9952136,0.0004670249,0.001776456,0.001333402,0.0006492706,0.0005602035],"domain_scores_gemma":[0.992278,0.002826015,0.0005767304,0.002890972,0.001266578,0.000161681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001894363,0.000882327,0.03844856,0.001230904,0.00005488403,2.981637e-7,0.003131668,0.000579756,0.001249536,0.7333729,0.0007949667,0.2202352],"study_design_scores_gemma":[0.0003975724,0.00007361803,0.01300111,0.0001512787,0.00004061459,0.000001440872,0.0004192999,0.589133,0.008548893,0.3847304,0.003159173,0.0003436296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1463049,0.0004057305,0.8069273,0.003282521,0.0003331307,0.001792175,0.00002358894,0.0002794531,0.04065118],"genre_scores_gemma":[0.9394483,0.00001575121,0.05927467,0.0004656514,0.00004671786,0.0002461398,0.00000442644,0.00001165068,0.0004866713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7931435,"threshold_uncertainty_score":0.99982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01941067974883095,"score_gpt":0.2874389405714528,"score_spread":0.2680282608226218,"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."}}