{"id":"W4408251921","doi":"10.1016/j.jss.2025.112408","title":"IoT systems testing: Taxonomy, empirical findings, and recommendations","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Concordia University","funders":"Canada Research Chairs","keywords":"Taxonomy (biology); Computer science; Data science; Software engineering; Biology; Ecology","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":[],"consensus_categories":[],"category_scores_codex":[0.001176112,0.0001509797,0.0004343762,0.0002467536,0.0002763486,0.0003902479,0.0003258942,0.0001237737,9.557873e-7],"category_scores_gemma":[0.0004676536,0.000109163,0.00005872337,0.0004088821,0.00005428626,0.0002736084,0.0001502062,0.0002450113,0.000002213325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007939696,"about_ca_system_score_gemma":0.00020472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007196473,"about_ca_topic_score_gemma":0.000001659191,"domain_scores_codex":[0.9984537,0.0001250796,0.0007716425,0.0002304045,0.0002186095,0.0002006035],"domain_scores_gemma":[0.9982398,0.0005990301,0.0003344928,0.0002739645,0.0004119572,0.0001408068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001755273,0.0001090582,0.9312065,0.001473342,0.0001680785,0.00003857384,0.000835634,0.0005558883,0.00004953324,0.002577381,0.02736551,0.03560299],"study_design_scores_gemma":[0.004269947,0.001489074,0.3729344,0.0110057,0.0002133631,0.005603434,0.003714867,0.06083066,0.00006568705,0.001350286,0.5371904,0.001332145],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6356016,0.01474609,0.3397997,0.002312737,0.006241061,0.0007544871,0.00001165904,0.0001805982,0.0003520133],"genre_scores_gemma":[0.9855614,0.00009647696,0.01364208,0.0001100715,0.0002003525,0.00002281555,4.343607e-7,0.000006838113,0.0003595034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5582721,"threshold_uncertainty_score":0.4451538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04560726939155958,"score_gpt":0.2913686906513986,"score_spread":0.245761421259839,"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."}}