{"id":"W4417026560","doi":"10.1007/s10664-025-10772-5","title":"Automatically Detecting Checked-In Secrets in Android Apps: How Far Are We?","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec","keywords":"Android (operating system); Obfuscation; Cloud computing; Mobile device; Empirical research; Humanoid robot","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":[0.0003160642,0.0002562925,0.0003522143,0.0005666331,0.00005364509,0.0001191202,0.0006170396,0.0001824153,0.000003682657],"category_scores_gemma":[0.00165448,0.0002761375,0.00007751057,0.001744642,0.00001916088,0.0004776289,0.0003530557,0.0005801294,0.000005098846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003523626,"about_ca_system_score_gemma":0.0000505357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007357057,"about_ca_topic_score_gemma":0.00002726375,"domain_scores_codex":[0.9982943,0.00004422102,0.0003699658,0.0005455876,0.0002352451,0.0005107075],"domain_scores_gemma":[0.9988573,0.0004657581,0.00007147007,0.0004616056,0.00004684608,0.0000969755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005692465,0.0005919705,0.2570586,0.002066787,0.0001138254,0.001510635,0.003268568,0.147817,0.009410609,0.00442767,0.001614124,0.5720633],"study_design_scores_gemma":[0.001283618,0.0001288037,0.19358,0.001836383,0.000008724407,0.00006730477,0.000104846,0.7412504,0.03450236,0.007383711,0.01847134,0.001382488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03958645,0.0003761879,0.9557555,0.001243638,0.0002346054,0.0002458997,9.4523e-7,0.002508333,0.00004837967],"genre_scores_gemma":[0.7168429,0.00002685836,0.2826951,0.0002191146,0.00002709261,0.0001045515,5.751594e-7,0.00002247987,0.00006122413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6772565,"threshold_uncertainty_score":0.9999691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01545296850898984,"score_gpt":0.2740933592147346,"score_spread":0.2586403907057447,"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."}}