{"id":"W4415256969","doi":"10.1109/tnsm.2025.3622149","title":"Active Learning for Transformer-Based Fault Diagnosis in 5G and Beyond Mobile Networks","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"VLSI and Analog Circuit Testing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Rogers Communications (Canada); University of Regina; University of Waterloo","funders":"","keywords":"Interpretability; Exploit; Dependency (UML); Novelty; Transformer; Artificial neural network; Active learning (machine learning); Fault detection and isolation","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":[0.001568733,0.001039025,0.001106889,0.001503279,0.0004396962,0.001012002,0.001879829,0.001307851,0.001056226],"category_scores_gemma":[0.004941025,0.0004001483,0.0008380273,0.0009156085,0.0007825002,0.001689082,0.001010713,0.001675606,0.000310345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054834,"about_ca_system_score_gemma":0.0006469492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003721063,"about_ca_topic_score_gemma":0.00443261,"domain_scores_codex":[0.9992642,0.0002065334,0.00004416499,0.000228254,0.0001746216,0.00008223468],"domain_scores_gemma":[0.9971233,0.002011481,0.0002263542,0.0001762702,0.0003846542,0.00007796041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000464567,0.0002521646,0.004189123,0.000147775,0.0001117924,0.0002343527,0.0001619558,0.5292419,0.00733943,0.008069512,0.00378594,0.4460015],"study_design_scores_gemma":[0.000005047576,0.00001898693,0.0001695905,0.000004366456,0.000007923456,0.00002228583,0.00000820981,0.9940759,0.00136627,0.00403116,0.0002867171,0.000003480442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02505338,0.0005067269,0.9720923,0.0003648268,0.00005077614,0.00004137365,0.0001222886,0.0009525581,0.0008158959],"genre_scores_gemma":[0.8392308,0.0004530975,0.1563918,0.0003842335,0.0001629057,0.0001049185,0.000577292,0.0001060703,0.002588873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003721063,"threshold_uncertainty_score":0.008296371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01127463560235892,"score_gpt":0.2401242517976746,"score_spread":0.2288496161953157,"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."}}