{"id":"W4308327073","doi":"10.1007/s10994-022-06263-z","title":"Adversarial examples for extreme multilabel text classification","year":2022,"lang":"fi","type":"article","venue":"Aaltodoc (Aalto University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Aalto-Yliopisto; Academy of Finland","keywords":"Adversarial system; Robustness (evolution); Computer science; Artificial intelligence; Similarity (geometry); Categorization; Text categorization; Machine learning; Pattern recognition (psychology); Data mining; Image (mathematics)","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":[0.00395352,0.001149205,0.001658903,0.001581527,0.000906621,0.001590741,0.002437756,0.002873585,0.005904712],"category_scores_gemma":[0.01406482,0.0006850861,0.001411399,0.001186832,0.001748482,0.002766746,0.004504499,0.004234289,0.002504038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038506,"about_ca_system_score_gemma":0.0007647218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001469714,"about_ca_topic_score_gemma":0.001852025,"domain_scores_codex":[0.9961354,0.001745088,0.0001792127,0.0007096559,0.000977563,0.0002532144],"domain_scores_gemma":[0.9909695,0.006545827,0.0004377556,0.001064628,0.0007330471,0.00024923],"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":[0.0005675997,0.0002401805,0.0007752969,0.0002727826,0.0001312364,0.0002118859,0.0001648835,0.5887283,0.004512968,0.0506481,0.0214006,0.3323462],"study_design_scores_gemma":[0.000008342251,0.00002413703,0.00007674128,0.00001351777,0.000004940971,0.00002991261,0.000008020384,0.9651326,0.001074311,0.03280817,0.0008117558,0.000007611224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008730514,0.0003435075,0.9871643,0.000461207,0.00009962804,0.0000594702,0.0002104326,0.001265875,0.001665074],"genre_scores_gemma":[0.495961,0.0004788589,0.4769781,0.0008839039,0.0005626003,0.0005475332,0.003230044,0.0009185341,0.02043947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005904712,"threshold_uncertainty_score":0.02090842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07888814776326718,"score_gpt":0.2577371208845423,"score_spread":0.1788489731212751,"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."}}