{"id":"W4391457419","doi":"10.1504/ijes.2023.136376","title":"<i>AR</i><SUP align=\"right\">2</SUP><i>PNET</i>: an adversarially robust re-weighting prototypical network for few-shot learning","year":2023,"lang":"en","type":"article","venue":"International Journal of Embedded Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Weighting; Computer science; 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":[0.00098364,0.001179688,0.0009519522,0.0007287689,0.0006007447,0.0007664955,0.002303926,0.001537397,0.003622178],"category_scores_gemma":[0.003129477,0.0004593437,0.0006756545,0.0006918692,0.0008645345,0.002637847,0.001695973,0.002270114,0.00133071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000762141,"about_ca_system_score_gemma":0.0007035771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004720676,"about_ca_topic_score_gemma":0.007585873,"domain_scores_codex":[0.9993721,0.0001239282,0.0000219112,0.0002717696,0.0001378118,0.00007248893],"domain_scores_gemma":[0.9992445,0.0001829892,0.00007165864,0.0002701603,0.0001594642,0.00007122735],"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":[0.0003438868,0.0001847013,0.001895981,0.0001651013,0.0001429776,0.0002601193,0.0001418541,0.4187691,0.02310825,0.01909226,0.01362927,0.5222665],"study_design_scores_gemma":[0.000007163921,0.00004937682,0.0002293046,0.000006417093,0.00001162258,0.00007381153,0.00001160759,0.985849,0.004224643,0.00816407,0.001362493,0.00001045718],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03255105,0.0004370922,0.9607816,0.0003322803,0.000149385,0.0001258607,0.0002810916,0.002302288,0.003039334],"genre_scores_gemma":[0.6761394,0.0004624051,0.305495,0.0006576958,0.000160861,0.0002246092,0.001798249,0.0004839876,0.01457785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004720676,"threshold_uncertainty_score":0.01211739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03182528465471989,"score_gpt":0.2903528276723231,"score_spread":0.2585275430176032,"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."}}