{"id":"W4411551950","doi":"10.1109/icse55347.2025.00224","title":"Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Deep neural networks; Pattern recognition (psychology); Machine learning","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":[0.0001084995,0.00005658562,0.00008244238,0.0001317687,0.00008644693,0.00003606265,0.0000934041,0.00006020501,9.430437e-7],"category_scores_gemma":[0.00001376169,0.00005419841,0.00001391268,0.0004237966,0.0000429373,0.0002010576,0.00009700208,0.00009545407,3.471699e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002356261,"about_ca_system_score_gemma":0.000007622878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002014208,"about_ca_topic_score_gemma":0.0001128656,"domain_scores_codex":[0.9994635,0.00002750302,0.0001671043,0.0002115994,0.00003529261,0.00009501517],"domain_scores_gemma":[0.9996769,0.00006674966,0.00004681295,0.0001534006,0.0000303969,0.00002567925],"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":[0.00001606557,0.00007717136,0.01921028,0.00003170835,0.000006563451,4.831273e-7,0.0001247827,0.0006687741,0.0183505,0.04184007,0.00000658328,0.919667],"study_design_scores_gemma":[0.000114002,0.00003215044,0.02794092,0.000006357461,0.000002607053,0.000002638732,0.00003257976,0.9615034,0.008383486,0.001884214,0.00005000889,0.0000476087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2687564,0.00006184477,0.7306032,0.0002392617,0.0000184943,0.0001414949,1.219963e-7,0.0000470088,0.0001321461],"genre_scores_gemma":[0.9791745,0.00006015329,0.02059502,0.00005858179,0.000006447593,0.00008212212,2.565218e-7,0.000002088965,0.00002086226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9608347,"threshold_uncertainty_score":0.2210147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0143051383237742,"score_gpt":0.2623590067592239,"score_spread":0.2480538684354497,"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."}}