{"id":"W4417150058","doi":"10.48550/arxiv.2503.16546","title":"A Comprehensive Survey on Architectural Advances in Deep CNNs: Challenges, Applications, and Emerging Research Directions","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Convolutional neural network; Inference; Feature learning; Feature extraction; Key (lock); Preprocessor; Big data; Natural language understanding; Feature (linguistics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005680869,0.0003489767,0.0004201314,0.0006544704,0.0004540224,0.00008303152,0.001384555,0.0001832546,0.000002153507],"category_scores_gemma":[0.0001440904,0.0003633834,0.0000683279,0.001374079,0.0002190624,0.0002194562,0.002250063,0.001733002,0.00003173943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001708916,"about_ca_system_score_gemma":0.0001109081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002315706,"about_ca_topic_score_gemma":0.002247481,"domain_scores_codex":[0.9963712,0.0006725973,0.0004644278,0.001533595,0.0003838823,0.0005742671],"domain_scores_gemma":[0.995541,0.002251501,0.0001718474,0.001578951,0.0003244444,0.0001322883],"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":[0.00004987111,0.0003185875,0.05638736,0.0004137944,0.00006051495,0.00001238128,0.001428114,0.023556,0.00009049637,0.02462746,0.0001480729,0.8929074],"study_design_scores_gemma":[0.0004063917,0.00008296243,0.8419003,0.0004777408,0.000009610731,0.00001045109,0.0001419466,0.01241603,0.0001573298,0.03783641,0.1058109,0.000749945],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3394696,0.290287,0.3299265,0.01917461,0.001572068,0.009587717,0.0002216266,0.001648354,0.008112561],"genre_scores_gemma":[0.8839844,0.09615254,0.01420586,0.0003549175,0.0002940827,0.004476145,0.0001259025,0.00004516894,0.0003609186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8921574,"threshold_uncertainty_score":0.9998818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1353104082551495,"score_gpt":0.3925663060686022,"score_spread":0.2572558978134527,"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."}}