{"id":"W4399899092","doi":"10.21203/rs.3.rs-4612382/v1","title":"A variable template matching algorithm for anomaly detection versus kernel density and gradient convolution algorithms and ResNet-50","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research & Development Corporation","funders":"","keywords":"Algorithm; Convolution (computer science); Kernel (algebra); Anomaly detection; Anomaly (physics); Variable (mathematics); Matching (statistics); Computer science; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics; Combinatorics; Physics","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":[0.001641543,0.001037266,0.001137338,0.002162952,0.0004312663,0.001432789,0.002028631,0.001420068,0.002374346],"category_scores_gemma":[0.003480565,0.0004200728,0.001005165,0.001928734,0.0006724368,0.002404417,0.000959746,0.001002609,0.001047807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290757,"about_ca_system_score_gemma":0.001271434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006411204,"about_ca_topic_score_gemma":0.005309472,"domain_scores_codex":[0.9988857,0.0001701775,0.00008154158,0.0003642183,0.0003693436,0.0001289622],"domain_scores_gemma":[0.9990262,0.0002260671,0.0001259354,0.0002178551,0.0003396294,0.0000643645],"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":[0.0003157575,0.0001796234,0.002982599,0.00008357775,0.0001545606,0.0001180356,0.00006433277,0.08120811,0.02418523,0.01293664,0.003709777,0.8740618],"study_design_scores_gemma":[0.00001097645,0.00005314473,0.0007385015,0.000004545222,0.00002133512,0.00009691227,0.00001085316,0.9762684,0.0188112,0.002572838,0.001395935,0.0000152221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03121713,0.000355804,0.9641647,0.0001729184,0.00009962182,0.00007669657,0.00006036264,0.002376347,0.001476376],"genre_scores_gemma":[0.3058555,0.0002933001,0.6890149,0.000128467,0.00006636834,0.0001015813,0.000438801,0.0003210023,0.003780103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006411204,"threshold_uncertainty_score":0.01274776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0509291035433329,"score_gpt":0.3572764019998762,"score_spread":0.3063472984565433,"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."}}