{"id":"W3101971338","doi":"10.1109/iemcon51383.2020.9284921","title":"Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Western University","funders":"Government of Canada","keywords":"Convolutional neural network; Anomaly detection; Artificial intelligence; Computer science; Residual; Metric (unit); Anomaly (physics); Pattern recognition (psychology); Task (project management); Similarity (geometry); Artificial neural network; Deep learning; Surface (topology); Machine learning; Image (mathematics); Algorithm; Engineering; Mathematics","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003993267,0.0004305737,0.0006394592,0.000163327,0.0001499725,0.0002487416,0.0001708365,0.001317017,0.00003609143],"category_scores_gemma":[0.00009767371,0.0004304902,0.0003519604,0.0003131459,0.00001959524,0.00008260075,0.00006383164,0.0009513905,0.000005288518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003569326,"about_ca_system_score_gemma":0.0001046199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003435982,"about_ca_topic_score_gemma":0.0001085047,"domain_scores_codex":[0.9981283,0.00008402095,0.0006855368,0.0005014971,0.0002366102,0.0003640272],"domain_scores_gemma":[0.9990872,0.0001502831,0.0001958955,0.0003315136,0.00009947197,0.0001356388],"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":[0.0002384455,0.000007621218,0.0001013282,0.0001438124,0.00008590015,0.000001900367,0.00001412784,0.9871749,0.002233059,0.00001025925,0.001338501,0.008650101],"study_design_scores_gemma":[0.001408174,0.0001049333,0.00002629143,0.0001583547,0.00008548245,0.000001591932,0.00002829733,0.9699708,0.01367901,0.00005248875,0.01400889,0.0004757285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1249942,0.0001862787,0.8617862,0.00002327744,0.01018523,0.001553726,0.00008199077,0.0008499579,0.0003391304],"genre_scores_gemma":[0.9950716,0.000006607803,0.0008892014,0.00002257791,0.003655276,0.0001343199,0.00007192403,0.0001056162,0.00004287433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8700774,"threshold_uncertainty_score":0.9999795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09690244408331108,"score_gpt":0.2638881365110323,"score_spread":0.1669856924277212,"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."}}