{"id":"W4404686190","doi":"10.1007/s10489-024-05892-2","title":"Dirichlet and Liouville-based normality scores for deep anomaly detection using transformations: applications to images and beyond images","year":2024,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Normality; Anomaly (physics); Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Latent Dirichlet allocation; Dirichlet distribution; Topic model; Statistics; Mathematics; Physics; Mathematical analysis","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":[0.0002713797,0.0001856163,0.0001498853,0.0002719455,0.0004803752,0.0004490679,0.0003027563,0.00007545853,0.00000522675],"category_scores_gemma":[0.00001107447,0.0001835308,0.00005222882,0.0008124074,0.0001258701,0.0004229796,0.00008352978,0.0001191731,0.00001291119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004956161,"about_ca_system_score_gemma":0.00004190252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004000037,"about_ca_topic_score_gemma":0.0000192673,"domain_scores_codex":[0.9987389,0.00001435812,0.0003288191,0.000551045,0.0001311842,0.0002357314],"domain_scores_gemma":[0.9991713,0.0001983212,0.00005513156,0.0003520475,0.00009826002,0.0001249471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001540472,0.00004865058,0.00003615331,0.0002083032,0.00002030185,5.371372e-7,0.0004263272,0.0007845986,0.04803298,0.1188783,0.00008257489,0.8314659],"study_design_scores_gemma":[0.00008204729,0.0001316185,0.0003649935,0.00003300778,0.00004253637,0.00002940566,0.0001708525,0.3083839,0.6462854,0.03328823,0.01074452,0.0004434141],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003815964,0.0006362961,0.9923448,0.0005811991,0.00004073427,0.001430332,0.0000353943,0.0004808068,0.0006344546],"genre_scores_gemma":[0.7792401,0.0001019366,0.2187908,0.0002731732,0.00004155506,0.001516624,0.000004964361,0.00001427872,0.00001655433],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8310225,"threshold_uncertainty_score":0.748417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01799972045383175,"score_gpt":0.2885207132515042,"score_spread":0.2705209927976724,"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."}}