{"id":"W6911501729","doi":"10.5281/zenodo.10373510","title":"Large Language Models vs. Stack Overflow in Addressing Android Permission Related Challenges","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Permission; Android (operating system); Modeling language; Stack (abstract data type); Language model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003881789,0.001126058,0.001326597,0.0010395,0.0009606168,0.00320463,0.001803697,0.002491422,0.003425314],"category_scores_gemma":[0.03511692,0.0007809942,0.001378638,0.0008143779,0.001824907,0.01247486,0.003361618,0.004558554,0.00133193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009557943,"about_ca_system_score_gemma":0.003403051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004316077,"about_ca_topic_score_gemma":0.008024552,"domain_scores_codex":[0.9949558,0.002113261,0.0002997585,0.0006102592,0.001471209,0.0005497044],"domain_scores_gemma":[0.9689468,0.02224082,0.001152827,0.00520984,0.001905499,0.0005441316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002466784,0.0009709523,0.01721752,0.001381317,0.0004633186,0.001474319,0.002959353,0.2753276,0.03675525,0.2004237,0.02352642,0.4370334],"study_design_scores_gemma":[0.00006529932,0.0001862162,0.0005874877,0.00009930084,0.000148035,0.0003478697,0.0004545834,0.8631753,0.00793408,0.12135,0.00559959,0.00005213947],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2829288,0.004313766,0.6756327,0.01230486,0.0006108575,0.0004070077,0.001293333,0.01157246,0.01093623],"genre_scores_gemma":[0.8963343,0.0009710107,0.09664103,0.001082209,0.0003121427,0.0001512778,0.0005786233,0.001139918,0.002789462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004316077,"threshold_uncertainty_score":0.02052909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05924810460344081,"score_gpt":0.2896069881760265,"score_spread":0.2303588835725857,"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."}}