{"id":"W3200804445","doi":"10.1145/3487019.3487026","title":"Designing UIs for Static Analysis Tools","year":2021,"lang":"en","type":"article","venue":"Queue","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Usability; Computer science; Workflow; Static analysis; False positive paradox; Human–computer interaction; Software engineering; Programming language; Artificial intelligence; Database","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":[0.0001493631,0.00006990074,0.0001396669,0.0001167228,0.00007957139,0.000126481,0.0002396118,0.00003059426,0.00002132023],"category_scores_gemma":[0.0002351522,0.0000736751,0.0001037429,0.000911042,0.00001028822,0.0003800005,0.00007613975,0.00005194353,0.000008463207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004386413,"about_ca_system_score_gemma":0.00005429335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006959475,"about_ca_topic_score_gemma":0.00001830673,"domain_scores_codex":[0.9992796,0.0000400072,0.0001416973,0.0002765704,0.0001045097,0.0001576155],"domain_scores_gemma":[0.9991044,0.0002387541,0.00005624209,0.0003974719,0.0001613944,0.00004167957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001533156,0.0001281596,0.0005366356,0.00009791741,0.0006600416,0.0001389486,0.001289243,0.00689643,0.07770119,0.1123895,0.006021872,0.7941247],"study_design_scores_gemma":[0.0001501405,0.00007538726,0.0003082604,0.00001089631,0.00007332645,0.000009742522,0.00005505118,0.04546385,0.9088028,0.02977087,0.0150606,0.0002190948],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005721538,0.00004813972,0.9980497,0.0003160734,0.00007124492,0.0001095879,0.000004370105,0.0003921293,0.0004366176],"genre_scores_gemma":[0.1349259,0.000006828895,0.8639556,0.0004080569,0.00002073791,0.00008529022,0.000005504883,0.000006320158,0.0005857641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8311016,"threshold_uncertainty_score":0.3004383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03207525565080939,"score_gpt":0.3028695785582222,"score_spread":0.2707943229074128,"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."}}